skillshare-changelog
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local git commands to interact with the repository's history and configuration. Evidence includes the use of
git describe --tags --abbrev=0to identify versions,git logto retrieve commit messages, andgit config user.nameto determine the user's identity for maintainer-only tasks. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its ingestion of repository data. Ingestion points: Commit messages are read via
git logand used to populate the changelog. Boundary markers: Absent; there are no specific markers or instructions provided to the agent to treat commit content as untrusted data or to ignore embedded instructions. Capability inventory: The agent is granted permission to write to and modifyCHANGELOG.md,website/src/pages/changelog.md, and generate release note files in thespecs/directory. Sanitization: Absent; the skill does not implement any validation or filtering of the commit message strings before they are processed by the language model to generate user-facing documentation.
Audit Metadata