trevorspray
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to review authentication-test results and raw responses from the TREVORspray tool, creating a surface where untrusted data could influence agent behavior.
- Ingestion points: The agent is directed to process raw HTTP responses and CLI output generated by the TREVORspray tool.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the external data.
- Capability inventory: The skill assumes the ability to execute the
trevorsprayCLI and access its output. - Sanitization: The skill advises redacting raw responses and distinguishing between valid and invalid results, which serves as a manual sanitization step.
Audit Metadata