stacksmith-review

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from git diffs and repository files to perform analysis and apply automated fixes.\n
  • Ingestion points: Untrusted data enters the agent context through git diff origin/$_BASE and file read operations during code, design, and security audits (SKILL.md).\n
  • Boundary markers: The skill does not implement explicit delimiters or instructions to ignore embedded commands within the content being reviewed.\n
  • Capability inventory: The skill has the ability to modify the repository using Write and Edit tools, and can execute git commit via the Bash tool to apply auto-fixes (SKILL.md).\n
  • Sanitization: No sanitization or validation logic is present to prevent malicious instructions embedded in reviewed code or commit messages from influencing the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 07:24 AM
Security Audit — agent-trust-hub — stacksmith-review