changelog-writer

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Git commit history and pull request descriptions to generate changelog content.
  • Ingestion points: Commit messages, PR titles, and issue references are ingested via git log commands defined in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded within the commit messages being analyzed.
  • Capability inventory: The skill utilizes subprocess calls to git, gh (GitHub CLI), and package managers like npm and cargo.
  • Sanitization: No explicit sanitization or filtering logic is provided for the commit content before it is interpolated into the final changelog or release notes.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands to perform repository analysis and automate release tasks.
  • Provides commands for git log, git describe, and git-cliff to parse version history.
  • Includes a shell script snippet (scripts/release.sh) that automates release creation using the GitHub CLI (gh release create).
  • [EXTERNAL_DOWNLOADS]: The skill suggests the installation of established open-source utilities for changelog automation.
  • Recommends the installation of conventional-changelog-cli via npm and git-cliff via cargo.
  • These recommendations point to official package registries and are standard tools for the described workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — changelog-writer