changelog
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides markdown documentation and templates for generating changelogs. All external links point to the author's public GitHub repository for the project.
- [COMMAND_EXECUTION]: The skill-command-recipes.md file contains Git command recipes (git log, git describe) for the agent to use when generating changelogs. These are standard, read-only operations for retrieving repository metadata.
- [PROMPT_INJECTION]: The skill processes commit messages extracted from the Git log, which are considered untrusted data from potentially many contributors.
- Ingestion points: Git log output retrieved via commands in skill-command-recipes.md.
- Boundary markers: Absent; there are no instructions to use delimiters for the interpolated commit text or to ignore embedded instructions.
- Capability inventory: The agent's capability is limited to text summarization and formatting for changelogs and announcements.
- Sanitization: Absent.
Audit Metadata