changelog-generator
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions.
- [NO_CODE]: The skill is composed entirely of natural language instructions, examples, and documentation. It does not include any scripts, binaries, or configuration files that execute code.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (git commit messages) to generate summaries.
- Ingestion points: Analyzes git commit history and project files like CHANGELOG_STYLE.md (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill does not provide or call any subprocesses, network tools, or executable functions.
- Sanitization: None specified for the input commits.
- Assessment: While the skill processes untrusted data, its lack of executable capabilities or network access renders the risk of indirect prompt injection negligible.
Audit Metadata