safe-debug
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted input from error logs or terminal output, creating an indirect prompt injection surface.\n
- Ingestion points:
scripts/safe_debug.pyreads user-provided text or files via command-line arguments.\n - Boundary markers: Absent; error content is directly embedded in output markdown files.\n
- Capability inventory: The skill is restricted to reading provided error files and writing diagnostic markdown reports to a local output directory.\n
- Sanitization: Absent; input text is truncated but not otherwise sanitized or escaped.
Audit Metadata