local-descriptions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection Surface. 1. Ingestion points: The skill fetches AI-generated markdown descriptions from api.search.brave.com via the local-descriptions endpoint. 2. Boundary markers: None specified; the agent receives raw markdown text without delimiters. 3. Capability inventory: No scripts, subprocess calls, or file-write operations are included in this skill. 4. Sanitization: No sanitization or escaping is performed on the externally sourced content, which is derived from third-party web context.
- NO_CODE (SAFE): The skill consists entirely of markdown documentation and cURL examples for an external API. It does not include Python scripts, Node.js packages, or binary executables.
Audit Metadata