changelog-generator

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or safety bypass attempts were detected. The skill is instructional and serves a legitimate productivity purpose.
  • [NO_CODE]: The skill consists exclusively of markdown instructions and YAML metadata. It does not include any scripts, binaries, or configuration files that execute logic on the host system.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing externally controlled data (git commit messages), which is a standard surface for this type of task.
  • Ingestion points: Git commit history as described in SKILL.md.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are included in the provided instructions for handling commit data.
  • Capability inventory: The skill definition does not include any scripts or subprocess calls; it relies on the agent's environment for git access.
  • Sanitization: No sanitization or filtering logic for the content of commit messages is specified within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:07 AM
Security Audit — agent-trust-hub — changelog-generator