code-review
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
git rev-parse,git log,git diff) withinSKILL.mdandcode-reviewer.mdto identify commit hashes and extract code changes for analysis. This is a core part of the skill's functionality and is performed on the local repository history.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes code changes that may contain malicious instructions in comments or strings. \n - Ingestion points: The
git diffoutput is directly interpolated into the subagent's prompt incode-reviewer.md.\n - Boundary markers: Absent. The diff content is not wrapped in specific delimiters or safety warnings to ignore instructions within the code.\n
- Capability inventory: The subagent has the capability to assess code and provide feedback which directly influences the developer's iteration loop, as described in
SKILL.md.\n - Sanitization: Absent. Code content is processed as raw text without validation or filtering.
Audit Metadata