non-commodity-content
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes content from external URLs provided by the user.
- Ingestion points: The
WebFetchtool is used in Step 1 ofSKILL.mdto retrieve content from user-supplied URLs. - Boundary markers: There are no explicit boundary markers or instructions to ignore potential commands or malicious patterns embedded within the fetched external content.
- Capability inventory: The skill is configured with broad capabilities, including
Bash,Read,Write,WebFetch, andWebSearchin theallowed-toolssection ofSKILL.md. - Sanitization: The skill lacks sanitization or validation of the fetched content beyond identifying its framing and structure for SEO purposes.
Audit Metadata