Agent Skills·Category ·Security
Category · 10,889 skills

Security agent skills

Security-audit, secrets-handling, dependency-scanning, and secure-coding skills. Teach any agent to find and fix vulnerabilities and to respect your security posture.

Browse all 10,889 Security skills →

Security
DashClaw
Approval and policy layer for agents: intercepts risky actions before they run and blocks or escalates them by rule. MIT.
hermesawesome-hermes-agentproductionapproval
Security
Anthropic-Cybersecurity-Skills
753+ structured cybersecurity skills mapped to MITRE ATT&CK. 31k★.
hermesawesome-hermes-skillsproductioncybersecurity
Security
keelwright
Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucinated packag…
openclawguardrailsloop-codingsecurity
Security
Stranger Recognition Skill | 陌生人识别技能
Identifies strangers appearing in surveillance areas through facial comparison; supports video stream and image detection, suitable for stranger warnings in residential communities…
openclawsurveillanceface-recognitionvideo-analysis
Security
x0x
Secure computer-to-computer networking for AI agents — gossip broadcast, direct messaging, CRDTs, group encryption. Post-quantum encrypted, NAT-traversing. Everything you need to b…
openclawnetworkingencryptioncrdt
Security
supply-chain-advisory
Audits dependency supply chains for bad versions, lockfile drift, and artifact integrity
openclawleylinesupply-chaindependencies
Security
writing-rules
Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior
openclawrulesmarkdownsafety
Security
content-sanitization
Provides sanitization guidelines for external content in skills and hooks
openclawsanitizationcontent-filterhooks
Security
hooks-eval
Evaluate hook security, performance, and SDK compliance. Use for audits
openclawhookssecurityperformance
Security
risk-classification
Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL)
openclawleylineriskclassification
Security
authentication-patterns
Provides auth patterns for API keys, OAuth, and token management
openclawauthoauthapi-keys
Security
osint-investigator
OSINT Investigator v2.1 — comprehensive open-source intelligence skill. Triggers on: OSINT, recon, digital footprint, dorking, social media investigation, username lookups, email t…
claude-codecodexcursorgemini-cliosintreconnaissancethreat-intel
Security
code-audit
Perform a structured audit of a codebase covering security, code quality, performance, dependencies, architecture, and testing hygiene, then produce a prioritized findings report. …
claude-codecodexcursorgemini-cliauditsecuritycode-quality
Security
misteye-security-check
This is the MistEye security gate skill. It is triggered by pre-installation risk checks (including Skill/MCP dependency manifests), pre-access security checks for domains or URLs,…
claude-codecodexcursorgemini-clisecurityiocsupply-chain
Security
defi-onchain-analytics
Use when profiling wallets, analyzing protocols or pools, inspecting token metrics, evaluating DEX liquidity or LP/vault performance, reading smart contract state, resolving proxy …
opencodeai-agent-skillblockchain-analyticsclaude-code-skill
Security
solana-auditor
Audit and research Solana smart contracts for security vulnerabilities and exploits. Use this skill whenever the user asks to audit, review, analyze, or security-test any Solana pr…
claude-codecodexcursorgemini-clisolanablockchainsmart-contracts
Security
wp-hardened-contact-form
Install a production-hardened contact form into a WordPress / Sage / Acorn theme. Ships a 9-layer defense stack (CSRF nonce, honeypot, timing, interaction count, gibberish heuristi…
claude-codecodexcursorgemini-cliwordpresssecuritycsrf
Security
fivem-audit
Performs comprehensive FiveM resource security, performance, and compatibility audits. Detects backdoors, RATs, SQL injection, event exploitation, NUI vulnerabilities, supply chain…
claude-codecodexcursorgemini-clifivemgtalua
Security
wp-malware-remediation
Analizar, detectar y limpiar malware PHP en sitios WordPress alojados en servidores Linux (CWP/cPanel). Cubre el ciclo completo: triage, backup, escaneo heurístico, clasificación d…
claude-codecodexcursorgemini-cliwordpressmalwarephp
Security
global-agent-guardrails
One shared denylist of catastrophic shell commands (rm -rf on / or ~, dd/mkfs, sudo rm, fork bombs, curl|sh, git push --force, gh repo delete) enforced as a PreToolUse/pre-exec gua…
claude-codeguardrailsshellsafety
Security
skills-keys
Manage API keys for the runner's --execute layer. CRUD on ~/.skills.env (chmod 600): list / add / update / remove / enable / disable gate flags / verify (ping vendor APIs) / export…
claude-codecodexcursorgemini-cliai:claudeai:geminiapi-keys
Security
ctfd-api
Work with any CTFd-platform CTF via its REST API (api/v1) as a player — list and read challenges, download attached files, submit flags (with correct handling of every attempt stat…
cursoropencodeapictfctfd
Security
amlclaw
AI-powered crypto AML compliance toolkit. Screens blockchain addresses against 40+ international regulations, generates compliance policies, and creates machine-readable detection …
claude-codecodexcursorgemini-cliamlcryptocompliance
Security
deepsafe-scan
Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt…
claude-codecodexcursorgemini-clisecurityscannersecrets
Security
Alepha188838884/context-firewall
Local proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery (measured: 122 tools → 4, ~28.6K tokens of definitions saved), compresses larg…
claude-codecodexcursorgemini-cliai-agentsclaudecontext-window
Security
1claw-hermes
TypeScript integration bringing [1Claw](https://1claw.xyz) to Hermes — MCP-based secret fetching from an HSM-backed vault, a [Shroud](https://docs.1claw.xyz/docs/guides/shroud) TEE…
hermesawesome-hermes-agentbetahsm
Security
dsv-forensische-erstsicherung
Coordinates forensic first-response after a data protection incident among client, internal IT, external forensic expert, and law firm. Covers forensic selection and engagement, ma…
claude-codecodexcursorgemini-cliforensicsdata-protectionincident-response
Security
truthfinder
Always-active web search safety skill. Classifies every website into SAFE, CAUTION, RISKY, or BLOCKED before reading or citing it. Reads and evaluates real user reviews and feedbac…
claude-codecodexcursorgemini-clitype:reviewweb-searchsafety
Security
qa
Use for paranoid, language-agnostic architectural code review — applies SOLID, DRY/KISS/YAGNI, decoupling, OWASP/NIST security, and quantitative complexity thresholds (cyclomatic >…
claude-codecodexcursorgemini-clisolidowaspnist
Security
symbiont
AI-native agent runtime with typestate-enforced ORGA reasoning loop, Cedar policy authorization, CommunicationPolicyGate for inter-agent governance, ToolClad declarative tool contr…
claude-codecodexcursorgemini-cliagentsecuritypolicy
Security
skill-security-reviewer
Security review and threat analysis for agent skills. Use when reviewing, auditing, or validating skills for security issues including prompt injection, code execution risks, data …
claude-codecodexcursorgemini-clisecurityauditthreat-modeling
Security
cyber-risk-modeling
Quantify cyber risk using FAIR methodology with Monte Carlo simulation, assess control effectiveness against NIST CSF/CIS/ISO 27001 frameworks, evaluate risk appetite alignment, an…
claude-codecodexcursorgemini-clifairriskmonte-carlo
Security
trafficwatch-ids-review
Skill específica para revisar, implementar, probar y documentar TrafficWatch IDS, un sistema académico de detección de intrusos con Python, Flask, Scapy, dashboard web, respuesta a…
claude-codecodexcursorgemini-cliidspythonflask
Security
salesforce-apex-quality
Apex code quality guardrails for Salesforce development. Enforces bulk-safety rules (no SOQL/DML in loops), sharing model requirements, CRUD/FLS security, SOQL injection prevention…
claude-codecodexcursorgemini-clisalesforceapexsecurity
Security
audit-trail-protokoll
Maintains an immutable audit trail logging every review run, prompt change, reviewer sign-off, cache hit, and hash verification. Records timestamp, action, responsible party, cube …
claude-codecodexcursorgemini-clitype:audittype:reviewaudit-log
Security
workflow-security-report
Triage a GitHub code-scanning (CodeQL) finding and generate an immutable Markdown report with an index entry, recommending remediation or dismissal, pinning every code reference to…
claude-codecodexcursorgemini-clitype:scannersecurityreport
Security
cyber-incident-response-72h
Structured immediate response for active cyber incidents — hacker attacks, ransomware, data exfiltration, insider threats. Phase 1: immediate containment, network isolation, forens…
claude-codecodexcursorgemini-cliincident-responsegdprforensics
Security
auditclaw-grc
GRC automation suite covering 13 frameworks (SOC 2, ISO 27001, HIPAA, GDPR, NIST CSF, PCI DSS, CMMC, FedRAMP, others). Manages controls, evidence, risks, policies, vendors, inciden…
claude-codecodexcursorgemini-clitype:audittype:reviewgrc
Security
ovhcloud-live-kms-key-destruction-guard
Gate and audit OVHcloud KMS key version destruction requests by enforcing five mandatory checks: confirmed key ID and KMS service URN, named approving identity, usage audit confirm…
claude-codecodexcursorgemini-clitype:auditovhcloudkms
Security
forter-agentic-readiness-audit
Audit a website against the Forter Agentic Readiness Guide. Loads the 25 weighted rubrics in `audit/`, probes the target site (and optional source code), scores each guideline Pass…
claude-codecodexcursorgemini-cliauditwebcompliance
Security
hack-review
Performs a scoped, coverage-led review of a working tree, staged diff, commit range, branch diff, PR, or suspicious implementation to identify hack-like risks such as impossible-st…
claude-codecodexcursorgemini-clitype:audittype:reviewcode-review
Security
integration-auth0
Connect Auth0 (identity + access management — users, roles, apps, actions, logs, org management) to a self-hosted Hermes Agent over SSH via the official auth0/auth0-mcp-server stdi…
claude-codecodexcursorgemini-cliauth0oauthidentity
Security
gcp-live-kms-key-destruction-guard
Gate Cloud KMS key version destruction and key ring deletion against a complete CMEK dependency audit. All Cloud SQL, GCS, BigQuery, Compute Engine disk, and Secret Manager resourc…
claude-codecodexcursorgemini-clicloud:gcptype:auditgcp
Security
cilium-network-policy-review
Use this skill for Cilium network policy review across Kubernetes NetworkPolicy, CiliumNetworkPolicy, and CiliumClusterwideNetworkPolicy formats, including L7 policy via Envoy, Clu…
claude-codecodexcursorgemini-clitool:k8stype:reviewcilium
Security
risk-control
Manages hazard and risk records for regulated projects via a single normalized YAML file (docs/.index/risk-file.yaml) with hazard IDs, risk estimates, controls, verification links,…
claude-codecodexcursorgemini-cliriskcomplianceyaml
Security
hipaa-review
Performs a HIPAA Security Rule compliance review across all Administrative, Physical, and Technical Safeguards in 45 CFR Part 164, Subpart C. Auto-invoked for healthcare data secur…
claude-codecodexcursorgemini-clitype:audittype:reviewhipaa
Security
ciphertext-recovery
ARM64 trace ciphertext recovery methodology. Use when given an ARM64 execution trace file and asked to reverse-engineer encryption, signature, or encoding algorithms from ciphertex…
claude-codecodexcursorgemini-cliarm64ciphertextcryptography
Security
pre-exec-check
Safety check before executing destructive or irreversible commands. Catches dangerous shell commands, risky git operations, secret exposure, and high-blast-radius actions before th…
claude-codecodexcursorgemini-clitype:reviewsafetyshell
Security
security-focused-review
Scoped security review establishing assets, trust boundaries, and attacker prerequisites with evidence-backed findings across auth, authorization, validation, injection, path handl…
claude-codecodexcursorgemini-clitype:reviewsecurityreview
Security
incident-materiality
Records cybersecurity incident materiality determinations across six factors—financial, operational, data, regulatory, reputational, and series assessment—capturing rationale, deci…
claude-codecodexcursorgemini-cliincidentcybersecuritycompliance
Security
iota-agent-mcp
IOTA blockchain MCP server providing wallet management with human-in-the-loop signing, Move smart contract build/test/publish, and on-chain queries via JSON-RPC and GraphQL. Use wh…
claude-codecodexcursorgemini-climcpiotablockchain
Security
dsv-beweissicherung
Structures evidence preservation after a data-protection incident to keep materials admissible in administrative, criminal, or civil proceedings. Covers chain of custody, secure lo…
claude-codecodexcursorgemini-cliforensicschain-of-custodycompliance
Security
threat-model
Analyzes systems and applications to produce structured threat model reports using STRIDE, OWASP Top 10, OWASP LLM Top 10, or MITRE ATT&CK frameworks. Use for traditional web appli…
claude-codecodexcursorgemini-clithreat-modelingstrideowasp
Security
supabase-security
Use when auditing or hardening a Supabase project's security posture. Triggers: scan/audit Supabase, RLS verification, find leaky tables, check anon grants, review SECURITY DEFINER…
claude-codecodexcursorgemini-clisupabaserlspostgres
Security
gcp-live-bigquery-dataset-deletion-guard
Gate BigQuery dataset deletion, table truncation, and authorized view changes against a full downstream dependency audit and export confirmation. Dataset deletion is immediate and …
claude-codecodexcursorgemini-clicloud:gcptype:auditgcp
Security
Invisible Unicode Injection Scan 不可視 Unicode コード注入検出
Detects invisible Unicode characters (tag characters, variation selectors, zero-width marks, bidi controls, anomalous whitespace) injected into source code diffs. Uses deterministi…
claude-codecodexcursorgemini-cliunicodesupply-chainstatic-analysis
Security
data-flow-review
Expert review pass examining data-flow, state ownership, lifetime, and boundary topology across every non-trivial entity—flagging ownership mismatches, incorrect dependency directi…
claude-codecodexcursorgemini-clitype:reviewdata-flowarchitecture
Security
auditing-skills
Scans AI agent skill directories for dangerous bash patterns, prompt injection, supply chain risks, and SKILL.md structure violations. Use when reviewing, validating, or security-a…
claude-codecodexcursorgemini-clisecurityauditprompt-injection
Security
dependa-audit
Supply-chain audit of a Dependabot PR. For every dependency the PR bumps, diff the current vs target version (install hooks, new deps, publisher/provenance, network endpoints, code…
claude-codecodexcursorgemini-clidependabotsupply-chaindependencies
Security
mcp-server-vet
Read-only safety inspection of a third-party MCP server before it is added to a config or trusted. Analyzes declared tools, schemas, scopes, transport, and secret surface, compares…
claude-codecodexcursorgemini-cliai:mcpmcpsecurity

Showing the top 60 of 10,889. See the full list →