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=0 to identify versions, git log to retrieve commit messages, and git config user.name to 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 log and 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 modify CHANGELOG.md, website/src/pages/changelog.md, and generate release note files in the specs/ 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
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:49 PM
Security Audit — agent-trust-hub — skillshare-changelog