post-implementation-review
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of implementation changes and touched files, which serves as a ingestion point for untrusted data. A malicious actor could theoretically embed instructions within code comments or documentation to influence the agent's review verdict.
- Ingestion points: The agent reads all files touched by an implementation (SKILL.md, Review Order steps 1 and 2).
- Boundary markers: Absent. The instructions do not specify delimiters for isolating code content.
- Capability inventory: The skill allows the agent to perform file writes (cleanup edits) and execute shell commands for diagnostics and testing.
- Sanitization: Absent. There are no instructions for sanitizing or escaping the content of the files being reviewed.
- [COMMAND_EXECUTION]: The skill instructs the agent to 'Run diagnostics and tests appropriate to the changed lane.' This involves executing shell commands which, in a development context, often includes running scripts defined in project configuration files (like package.json or Makefiles). This is a standard capability for development-oriented skills.
Audit Metadata