canonical-url
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit rendered HTML and HTTP response headers from external websites, which constitutes an ingestion point for untrusted data that could contain malicious instructions.
- Ingestion points: The skill processes rendered HTML, structured data, and HTTP response headers as specified in the description and Code Review sections of
SKILL.md. - Boundary markers: There are no specific instructions or delimiters provided to the agent to treat the audited HTML or header content as untrusted or to ignore embedded instructions within that data.
- Capability inventory: The skill focuses on analysis, verification, and code review. It does not contain scripts or instructions for autonomous file system modifications or network exfiltration.
- Sanitization: No sanitization or filtering protocols are defined for the data ingested during the audit process.
Audit Metadata