panic-room-finder
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Risk. Ingestion points: The skill allows the use of the WebFetch tool for external data entry. Boundary markers: No delimiters or instructions are provided to distinguish external content from the skill's own logic. Capability inventory: The skill is permitted to use the Bash tool and file system editing commands (Read, Write, Edit). Sanitization: There is no instruction for sanitizing or escaping data retrieved from external sources.
- [NO_CODE]: The skill is composed entirely of Markdown documentation and templates. No executable scripts in Python, Node.js, or other programming languages are included in the skill files.
Audit Metadata