audit-content
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content (articles, brand DNA files) and fetches data from the web (URLs, search results). Malicious instructions hidden in these sources (e.g., in HTML comments or within text being audited) could attempt to influence the agent's behavior during the audit process. The skill lacks explicit sanitization or instruction-guarding steps for this external data.
Audit Metadata