crypto-review
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code provided at runtime via the $ARGUMENTS variable or the current working directory. Maliciously crafted code or comments within the target repository could attempt to subvert the agent's auditing logic, influence its findings, or exploit its tool access.\n
- Ingestion points: Source code files accessed via Read and Glob tools as specified in the Audit Procedure.\n
- Boundary markers: No delimiters or instructions to ignore embedded commands within the analyzed code are present.\n
- Capability inventory: The skill is allowed to use Bash, Task, Read, Glob, and Grep tools, providing a significant capability set if an injection occurs.\n
- Sanitization: No sanitization, escaping, or validation of the untrusted codebase content is performed prior to the agent's analysis.
Audit Metadata