30x-seo-images
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary purpose is performing technical image audits. All instructions are consistent with its stated purpose, and no malicious command execution or data exfiltration patterns were found. The mention of emerging formats like JPEG XL is purely informational.- [INDIRECT_PROMPT_INJECTION]: The skill processes external data, which creates a potential vulnerability surface.
- Ingestion points: Fetches external web content (HTML, images) using the WebFetch tool as defined in the allowed-tools configuration.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard potential instructions found within the audited content (e.g., in alt text or metadata).
- Capability inventory: The skill is restricted by frontmatter to WebFetch and Read tools, lacking high-risk capabilities like arbitrary shell execution or file writes.
- Sanitization: No specific filtering or sanitization of external content is defined.
Audit Metadata