article-enrichment
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted article content, which is a potential surface for indirect prompt injection. \n
- Ingestion points: Raw article text is read from media/articles/ via gbrain get (SKILL.md). \n
- Boundary markers: Absent; the prompt does not use delimiters to isolate article content. \n
- Capability inventory: The skill is limited to querying, reading, and writing brain pages via gbrain (SKILL.md). \n
- Sanitization: Absent; content is processed directly for summarization. \n- [COMMAND_EXECUTION]: The skill uses the gbrain CLI for its primary functions. These commands are consistent with the skill's purpose and are used to manage content within a specific directory.
Audit Metadata