merge-branch

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Git repositories which creates an attack surface for indirect prompt injection.
  • Ingestion points: Untrusted content is brought into the agent context via git log and git show in modes/integrate.md (Step 2), git diff in modes/integrate.md (Step 6), and rg in modes/integrate.md (Step 7) and modes/audit.md.
  • Boundary markers: The skill instructions do not utilize delimiters or specific instructions to prevent the agent from following commands that might be present in commit messages or file contents.
  • Capability inventory: The agent is empowered to modify local files and execute Git operations (git merge), which could be manipulated if the agent obeys instructions found within the data it is auditing.
  • Sanitization: There is no mechanism described to sanitize, filter, or escape the repository data before it is presented to the LLM for reasoning.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 12:59 AM
Security Audit — agent-trust-hub — merge-branch