From hydra-vuln-detector
Use when the developer asks about vulnerabilities, OWASP issues, CWE findings, or security weaknesses in their code. Auto-triggers on: "vulnerabilities", "OWASP", "CWE", "security issues", "SQL injection", "XSS", "is this code safe", "security scan".
How this skill is triggered — by the user, by Claude, or both
Slash command
/hydra-vuln-detector:vuln-awarenessThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<purpose>
<decision_tree> IF user asks about a specific vulnerability: → Read ${CLAUDE_PLUGIN_ROOT}/state/audit.jsonl → grep for "vuln_detected" events with matching CWE → Show: CWE, description, file, line, severity → Provide specific fix code
IF user asks for full OWASP scan: → Run: python3 ${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/vuln-scanner.py . → Group results by OWASP category → Show most critical first
IF user asks about supply chain: → Run: python3 ${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/supply-chain.py . → Show phantom dependency findings → Suggest package verification steps
IF no findings: → "No vulnerabilities detected. Hydra monitors Write/Edit for OWASP Top 10 patterns." </decision_tree>
<output_format>
| File | Line | CWE | Description | Severity |
|---|---|---|---|---|
| ... | ... | CWE-89 | SQL injection via concatenation | Critical |
Fix:
# Before (vulnerable):
query = "SELECT * FROM users WHERE id=" + user_id
# After (safe):
cursor.execute("SELECT * FROM users WHERE id = %s", (user_id,))
...
Summary: [N] vulnerabilities | [N] CWE types | [N] files affected </output_format>
<escalate_to_sonnet> IF critical injection or deserialization vulnerabilities found: "ESCALATE_TO_SONNET: critical injection vulnerability — deep context analysis needed" IF more than 5 OWASP categories affected: "ESCALATE_TO_SONNET: broad vulnerability surface — architectural review needed" </escalate_to_sonnet>
npx claudepluginhub enchanter-ai/hydra --plugin vuln-detectorProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.