flows-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executenpm outdated,npm audit, and test runners such asvitestandjest. These commands are used to perform technical audits of the project's dependencies and code coverage as part of the review process. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface. Ingestion points: The skill reads local TypeScript files (.ts, .tsx) and other skill configuration files (SKILL.md) to gather guidance and analyze code. Boundary markers: No explicit delimiters or instructions are provided to help the agent ignore or bypass potential instructions embedded within the analyzed source code. Capability inventory: The agent has access to
Bash,Write,Read,Glob, andGreptools. Sanitization: Content from the ingested files is processed without filtering or sanitization steps to neutralize embedded instructions.
Audit Metadata