article-enrichment
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes raw article text dumps which are considered untrusted data and could contain embedded instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads raw content from article files located in
media/articles/using thegbrain getcommand (defined in SKILL.md). - Boundary markers: While the skill instructs the agent to wrap the original raw source in a
<details>block in the output, it does not explicitly instruct the agent to ignore instructions that might be contained within that raw text during the enrichment process. - Capability inventory: The skill has the ability to read files, query the brain via
gbrain, and write new structured pages tomedia/articles/usingput_page. - Sanitization: There is no evidence of filtering, escaping, or validation of the article content to remove potential prompt injection vectors before the agent processes the text.
Audit Metadata