author-info
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external, untrusted data as part of its primary auditing function.
- Ingestion points: The skill instructions specifically direct the agent to "Verify the rendered HTML and HTTP response" (SKILL.md) and "Inspect rendered HTML and HTTP headers" (references/rule.md) of arbitrary web pages.
- Boundary markers: There are no explicit instructions, such as XML-style delimiters or specific safety warnings, to prevent the agent from being influenced by malicious instructions embedded in the HTML or metadata being audited.
- Capability inventory: The skill description implies the use of web-fetching and inspection capabilities to perform the audit.
- Sanitization: There are no mentions of sanitizing, filtering, or escaping the external content before processing it within the agent's context.
Audit Metadata