prowler-docs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface (Category 8). 1. Ingestion points: Untrusted content may enter via WebFetch and Read tools during documentation tasks. 2. Boundary markers: The skill lacks explicit instructions or delimiters to prevent the agent from following commands potentially embedded in documentation. 3. Capability inventory: The presence of Bash and Write tools allows for high-impact actions if the agent is misled. 4. Sanitization: No sanitization of processed data is defined in the instructions.
- [COMMAND_EXECUTION] (LOW): Excessive Tool Permissions. The skill requests Bash and WebFetch capabilities in its metadata. These tools provide a capability tier that exceeds the requirements of a documentation style guide and increases the potential attack surface.
- [NO_CODE] (SAFE): The provided files consist entirely of Markdown text and metadata with no executable scripts, binaries, or obfuscated code detected.
Audit Metadata