skills/codexstar69/bug-hunter/hunter/Gen Agent Trust Hub

hunter

Warn

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute Node.js scripts (doc-lookup.cjs and context7-api.cjs) located in a directory defined by the $SKILL_DIR environment variable. This pattern of executing code from a dynamically computed path represents a risk if the environment configuration is manipulated.\n- [PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection because it is designed to ingest and analyze untrusted files from external codebases.\n
  • Ingestion points: External codebase files provided in the assignment for analysis (Phase 1).\n
  • Boundary markers: Absent. No delimiters or instructions to ignore embedded instructions within analyzed files are provided.\n
  • Capability inventory: Capability to write JSON findings to the local filesystem (.bug-hunter/findings.json) and execute helper scripts via the shell.\n
  • Sanitization: Absent. The instructions do not mention sanitizing or escaping the content read from files before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 1, 2026, 08:09 AM
Security Audit — agent-trust-hub — hunter