changelog-generator
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection due to its intended purpose of processing and transforming untrusted external data.
- Ingestion points: Scans and analyzes git commit history, which can contain arbitrary text provided by any contributor (SKILL.md).
- Boundary markers: There are no instructions provided to the agent to use delimiters or to treat the commit content as untrusted data to avoid command leakage.
- Capability inventory: The skill directs the agent to read file system history and explicitly suggests writing the processed output directly to a local file, specifically
CHANGELOG.md(SKILL.md). - Sanitization: No sanitization, filtering, or validation steps are defined for the commit messages before they are processed and written to the file system.
- [NO_CODE]: The skill is composed entirely of markdown instructions and documentation. It does not include any accompanying scripts (Python, JavaScript, shell), binaries, or configuration files that would execute automated logic outside of the LLM's response generation.
Audit Metadata