content-decay-detector
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the internet via search results to detect content decay patterns. \n
- Ingestion points: External web content and search snippets retrieved during the discovery and decay signal checking phases in SKILL.md. \n
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions found within retrieved web content. \n
- Capability inventory: The skill utilizes
web_searchand generates textual optimization reports based on input data. \n - Sanitization: No explicit sanitization or validation of external web data is defined before processing.
Audit Metadata