changelog-generator

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is entirely descriptive and does not include any scripts, binaries, or executable content.
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were found. The skill operates on the user's local git repository as intended for its described purpose.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection, as it is designed to ingest and process external data.
  • Ingestion points: Local git commit history and user-provided style guide files (e.g., CHANGELOG_STYLE.md) in the SKILL.md file.
  • Boundary markers: The instructions do not define explicit delimiters to separate untrusted commit data from the agent's instructions.
  • Capability inventory: The skill requires the agent to use its existing capabilities to read file contents and execute git commands to retrieve history.
  • Sanitization: No explicit sanitization or filtering of commit message content is suggested in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 03:29 PM
Security Audit — agent-trust-hub — changelog-generator