dev-swarm-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill provides structured instructions for an AI agent to perform code audits, including checking for OWASP Top 10 vulnerabilities.
- [COMMAND_EXECUTION]: The skill utilizes Git commands (
git add,git commit,git reset) to manage review documentation and backlog updates. These operations are restricted to the local project repository and are consistent with the skill's stated purpose of tracking review findings. - [PROMPT_INJECTION]: The skill includes strong instructional markers (e.g., "CRITICAL", "IMPORTANT") to guide the agent's workflow, but these do not attempt to bypass safety filters or override core system instructions.
- [DATA_EXPOSURE]: The skill requires access to project-specific folders (e.g.,
/features,/10-sprints,{SRC}/) to perform its function. This is standard for a code review tool and does not involve accessing sensitive system files or credentials.
Audit Metadata