changelog-generator
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing external, potentially untrusted data from commit logs and local files.
- Ingestion points: Git commit history and user-supplied
CHANGELOG_STYLE.mdfiles. - Boundary markers: Absent. The skill does not define specific delimiters to separate untrusted input from the agent's core instructions.
- Capability inventory: The skill uses file system read capabilities (via git logs) and suggests writing to the local file system (CHANGELOG.md).
- Sanitization: Absent. No explicit filtering or sanitization of the commit messages is required by the instructions.
Audit Metadata