content-pillar-atomizer
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses the
web_fetchtool to retrieve external content from user-specified URLs provided in thepillar_contentvariable. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of external content.
- Ingestion points: The
pillar_contentfield inSKILL.mdaccepts untrusted strings or URLs. - Boundary markers: Absent; there are no instructions to the model to ignore potential commands contained within the
pillar_content. - Capability inventory: The skill utilizes
web_fetch(documented inSKILL.md) for network read operations. - Sanitization: Absent; the skill does not define methods to sanitize or escape the input content before it is used for generation.
Audit Metadata