git-workflow-automation

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes and executes several local bash scripts (scripts/generate-changelog.sh, scripts/next-version.sh, scripts/validate-commits.sh) and standard Git CLI commands to automate repository management. These scripts perform operations such as reading commit history and writing to the CHANGELOG.md file.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted Git commit messages.
  • Ingestion points: Commit history data enters the agent context via git log commands within the provided scripts.
  • Boundary markers: No delimiters or 'ignore embedded instructions' warnings are used when processing commit data.
  • Capability inventory: The skill can execute shell commands and perform file writes through the automation scripts.
  • Sanitization: The skill lacks sanitization or validation of the commit message content before it is used for changelog generation or versioning logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:39 AM
Security Audit — agent-trust-hub — git-workflow-automation