studio-develop-code-review

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the local repository, including diffs, untracked files, and documentation, which could contain malicious instructions designed to influence the agent's behavior during the review process.
  • Ingestion points: According to SKILL.md (Workflow Step 1), the agent reads outputs from git diff, git ls-files --others, and project-specific files like CLAUDE.md and docs/PRD.md.
  • Boundary markers: The instructions do not define any delimiters or explicit 'ignore instructions' warnings to prevent the agent from following commands embedded within the code changes being reviewed.
  • Capability inventory: The skill uses git to read repository state and file contents. It does not contain instructions for external network access or file modifications.
  • Sanitization: There are no protocols described for sanitizing or escaping the external content before it is processed in the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:33 PM
Security Audit — agent-trust-hub — studio-develop-code-review