audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to capture and analyze content from arbitrary external URLs provided in the
$ARGUMENTS. This creates a surface for tool output poisoning if the target website contains malicious instructions specifically crafted to influence the AI agent's audit behavior or surrounding context.
Audit Metadata