kf-g-agent-review-post-implementation-two-stage
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for a human-like code review process divided into two stages: a blind diff review and a requirements alignment review. No malicious patterns, such as prompt injection, obfuscation, or unauthorized data access, were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of code diffs and implementation plans. While this constitutes an attack surface, the skill does not request any tool permissions in its frontmatter (empty allowed-tools), which effectively prevents technical exploitation. The instructions mandate a highly structured output format using markdown tables, which acts as a boundary to prevent instructions within the analyzed data from influencing the agent's behavior.
Audit Metadata