reviewing-code
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code using tools such as Read, Grep, and Glob. This establishes a potential vector for indirect prompt injection if the code under review contains malicious instructions disguised as comments or documentation.
- Ingestion points: File content retrieved through filesystem tools (Read, Grep, Glob).
- Boundary markers: The instructions do not define specific delimiters or security warnings to separate external code data from the agent's internal instructions.
- Capability inventory: The skill environment allows access to the Bash tool, which could be targeted by successful injection.
- Sanitization: No explicit logic is provided to sanitize, escape, or filter instructions embedded within the ingested code content.
Audit Metadata