qa-reviewer
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues, obfuscation, or data exfiltration patterns were detected. The skill's functionality is consistent with its stated purpose as a QA reviewer.
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard utilities like ls, grep, find, and git for project inspection and verification.
- [COMMAND_EXECUTION]: A template command for a Python-based syntax check is provided in references/full-guide.md to verify markdown formatting by counting code block delimiters locally.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project files, which presents a surface for indirect prompt injection.
- Ingestion points: Reads project files, requirement documents, and internal rule files as specified in references/full-guide.md.
- Boundary markers: Absent; the instructions do not specify the use of delimiters when reading external content for review.
- Capability inventory: Local execution capabilities including shell command execution and local Python script execution.
- Sanitization: Absent; the skill does not explicitly describe sanitization or escaping of the content being reviewed.
Audit Metadata