adversarial-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze code provided by users, which serves as a vector for indirect prompt injection.
- Ingestion points: The untrusted data enters the agent context through the code provided for review.
- Boundary markers: The instructions lack explicit boundary markers or warnings to disregard instructions that might be embedded within comments or string literals in the code under review.
- Capability inventory: The skill has no dangerous capabilities; it does not utilize file writing, network requests, or subprocess execution.
- Sanitization: There is no evidence of sanitization or input validation performed on the ingested code to prevent adversarial content from influencing the agent's behavior.
- [NO_CODE]: The skill is composed entirely of markdown instructions in the SKILL.md file and does not include any accompanying scripts, binaries, or configuration files that would execute code.
Audit Metadata