changelog
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard
gitandgh(GitHub CLI) commands to retrieve repository history, diff statistics, and pull request information. These are well-known tools used for their intended purpose in a developer workflow. - [SAFE]: The instructions mandate that the agent must present the user with a draft before saving any changes to the
CHANGELOG.mdfile, which is a key safety measure for tools that modify local files. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) because it processes untrusted data from the repository's history.
- Ingestion points: Commit messages, Pull Request titles/descriptions, and data from issue trackers.
- Boundary markers: None are explicitly defined in the prompt instructions to isolate the ingested data.
- Capability inventory: The skill can execute shell commands (
git,gh) and write to the local file system (CHANGELOG.md). - Sanitization: The skill relies on the agent's logic to summarize content into outcome-focused entries, but does not provide explicit technical sanitization steps.
Audit Metadata