recon-fire-restoration
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches certificate transparency data from 'crt.sh', which is a well-known and reputable service used by security researchers for domain discovery. This operation is limited to querying public logs and does not involve downloading executable scripts.
- [COMMAND_EXECUTION]: Phase 2 includes a command that pipes target API output to 'python3 -m json.tool'. This is a built-in Python module dedicated to formatting and pretty-printing JSON data; it does not evaluate or execute the content, and thus poses no risk of remote code execution despite the automated scanner alert.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it instructs the agent to ingest and process data from external sources (target REST APIs and debug logs) without specific sanitization. However, this risk is mitigated by the skill's intended use-case as a security auditing tool.
- Ingestion points: Data fetched from 'wp-json/' and 'debug.log' in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: Shell commands (curl) and local data formatting (python3).
- Sanitization: Absent.
Audit Metadata