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
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM