Hermes Repo Scanner — Security skill for Claude Code
Pre-install security scanner for Hermes Agent skills — 68 patterns across 10 categories, OWASP ASI-mapped.
How to install Hermes Repo Scanner
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open JPeetz/hermes-repo-scanner and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Hermes Repo Scanner does
Pre-install security scanner for Hermes Agent skills — 68 patterns across 10 categories, OWASP ASI-mapped.
Alternatives in Security
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
- Skill Audit — Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review 2.8k ★
- Install — Install the Damage Control security hooks system 456 ★
README
Hermes Repo Security Scanner
Pre-install security scanner for Hermes Agent skills. Scans repos for hardcoded secrets, prompt injection, code execution, supply chain threats, Unicode obfuscation, MCP poisoning, memory poisoning, and more — mapped to the [OWASP Top 10 for Agentic Applications (ASI01-ASI09)](https://genai.owasp.org).
Combines pattern sets from CodeFlow + Hermes `skills_guard.py` + OWASP ASI.
Quick Start
# Install as a Hermes plugin
git clone https://github.com/JPeetz/hermes-repo-scanner ~/.hermes/plugins/repo-scanner
# Scan a repo before installing it
python3 ~/.hermes/plugins/repo-scanner/scanner.py scan https://github.com/user/repo
# Or use the wrapper that prompts before install
python3 ~/.hermes/plugins/repo-scanner/wrapper.py install https://github.com/user/repo
# JSON output for programmatic use
python3 ~/.hermes/plugins/repo-scanner/scanner.py scan https://github.com/user/repo --json
68 Detection Patterns Across 10 Categories
| Category | Patterns | Severity | ASI |
|---|---|---|---|
| Code execution | eval(), exec(), os.system(), subprocess, compile() | 🔴🟡 | ASI05 |
| Tool misuse | SQL injection, XSS (innerHTML, document.write) | 🔴 | ASI02 |
| Supply chain | curl/wget/requests with secrets, base64 env, SSH/.aws/.kube access | 💀🟡 | ASI04 |
| Prompt injection | Ignore instructions, role hijack, system prompt override, hidden HTML | 💀🔴 | ASI04 |
| Destructive | rm -rf /, chmod 777, mkfs, dd, truncate | 💀🔴 | ASI05 |
| Persistence | crontab, shell rc, authorized_keys, sudoers, launchd | 🔴🟡 | ASI03 |
| Network | reverse shell, tunnel services, webhook exfil, paste services | 💀🔴🟡 | ASI07 |
| Memory poisoning | memory[] writes, memory API calls, persist() calls | 🔴🟡 | ASI06 |
| MCP poisoning | MCP server config, register_mcp, mcp_server blocks | 🔴 | ASI02 |
| Unicode obfuscation | U+E0000-E0FFF tag chars, zero-width, bidi overrides | 🔴🟡 | ASI04 |
Scoring
| Verdict | Score | Me
Related Skills
Cpv Pre Install Scan
Scan any skill / plugin / marketplace for security threats BEFORE installing it. Runs the MANDATORY native ski
Skill Lint
Security scanner for Claude Code / agent skills. Catches prompt injection, obfuscation, credential exfiltratio
Claude Skill Antivirus
Security scanner for Claude Code Skills — 9 engines detect malicious patterns, data exfiltration, dangerous op
Horde Test Skill
Execute comprehensive testing plans using horde-swarm to dispatch parallel test agents across multiple test ca
Agent Assurance
Declare what your AI agent may do. Verify it on every edit, PR and release — MCP configs, Claude Code permissi
Skillguard
Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads befo
Related Agents
Security Adversary
Red-team security reviewer for in-flight code diffs. Reads a git diff and produces a ranked critique focused o
Kavach History
KAVACH git-history forensics specialist. Mines commit history for security-relevant commits with no CVE/GHSA l
QA Release Engineer
Pre-release scanner that audits code for release readiness across multiple quality dimensions