kmcp-dev-release-semver

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands including git, npm, and gh to perform repository management tasks such as branch creation, version bumping, and pull request generation. These operations are restricted to the local environment and the project's official repository.
  • [PROMPT_INJECTION]: The skill implements a workflow that analyzes git log output to recommend semantic versioning levels. This represents a potential surface for indirect prompt injection, as malicious commit messages could attempt to influence the agent's logic.
  • Ingestion points: Output of git log (SKILL.md, Section 1).
  • Boundary markers: None present to isolate the commit message content from the agent's instructions.
  • Capability inventory: Local file modifications, branch management, git push operations, and PR creation via gh CLI.
  • Sanitization: No explicit sanitization or filtering of commit message content is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 07:39 AM
Security Audit — agent-trust-hub — kmcp-dev-release-semver