release-skills

Fail

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: CRITICALCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git and GitHub CLI (gh) to perform legitimate release operations, such as viewing commit logs, tagging releases, and pushing changes to remote repositories.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from git commit logs and pull request metadata to perform its core logic.
  • Ingestion points: Commit messages retrieved via git log and pull request author information from gh pr view are used to generate changelog content.
  • Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands within the commit messages being processed.
  • Capability inventory: The skill has the ability to write to project configuration files (e.g., package.json, pyproject.toml) and execute network-based commands (git push).
  • Sanitization: There is no evidence of sanitization or escaping of the commit messages before they are incorporated into the changelog or used to determine version bump recommendations.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 24, 2026, 11:22 AM