skills/dnd-mapp/agent-skills/commit/Gen Agent Trust Hub

commit

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands to interact with Git, including git status, git diff, git log, git add, and git commit. These operations are standard for the skill's purpose of repository management and are restricted to the local filesystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's working tree via git diff. This presents a potential surface for indirect prompt injection if the files being committed contain malicious instructions.
  • Ingestion points: git diff output processed in SKILL.md (Step 1).
  • Boundary markers: The skill relies on natural language instructions for grouping but does not use explicit boundary markers for the diff content.
  • Capability inventory: Access to git add and git commit commands in SKILL.md (Step 7).
  • Sanitization: None explicitly mentioned, however, the skill mandates a manual review step in SKILL.md (Step 6), where the user must approve the proposed commit plan before any changes are applied, effectively mitigating the risk of automated exploitation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:09 PM
Security Audit — agent-trust-hub — commit