fog-scout
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is intended to sweep unfamiliar codebases for information, which introduces an indirect prompt injection vector if the codebase contains malicious hidden instructions.
- Ingestion points: The skill reads "unfamiliar territory," including modules, history, and dependencies from the user's codebase as defined in SKILL.md.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the prompt instructions.
- Capability inventory: The skill is limited to read-only territory access and writing findings to a ledger using the
fogskill; it does not request shell execution or network access within the SKILL.md definition. - Sanitization: There is no evidence of sanitization or filtering of the codebase content being processed.
Audit Metadata