red-team-verifier-patrick-munro
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted AI-generated legal documents, creating an attack surface for indirect prompt injection.
- Ingestion points: Legal content is ingested for review in
SKILL.md(Step 1: Initial content review). - Boundary markers: The instructions do not specify the use of clear delimiters or boundary markers to isolate the untrusted document from the agent's core instructions.
- Capability inventory: The agent is directed to use web search tools to verify claims and generate detailed reports based on the input text.
- Sanitization: The skill lacks explicit instructions for the agent to sanitize or escape potentially malicious prompts within the legal text being analyzed.
Audit Metadata