skills/ericmjl/skills/atomic-commits/Gen Agent Trust Hub

atomic-commits

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands including git status, git diff, git add, and git commit to manage repository history.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. 1. Ingestion points: File changes are ingested via git diff commands in SKILL.md. 2. Boundary markers: No delimiters are used to isolate ingested data. 3. Capability inventory: The agent can modify the repository using git add and git commit. 4. Sanitization: Content from diffs is not sanitized before being used to generate commit messages.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 12:04 PM
Security Audit — agent-trust-hub — atomic-commits