prepare-changelog

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands for Git operations, including git fetch, git log, git diff, git checkout, git commit, and git push. These operations are essential for the skill's stated purpose of release management.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through the ingestion of untrusted repository data.
  • Ingestion points: Commit subjects extracted via git log and file summaries from git diff during the change listing phase.
  • Boundary markers: Absent. The skill does not employ specific delimiters or warnings to the agent when processing commit data.
  • Capability inventory: Includes file system write access (CHANGELOG.md), shell command execution (git), and GitHub API interaction via MCP (mcp_github_create_pull_request).
  • Sanitization: Absent. Commit content is interpolated directly into the draft changelog and pull request body without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:13 PM
Security Audit — agent-trust-hub — prepare-changelog