app-store-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process git commit messages, which are external data sources that could theoretically contain malicious instructions. However, the risk is negligible as the skill only performs read-only operations and produces text-based summaries without dangerous capabilities like network access or file system modification.
- Ingestion points: Commit history retrieved via
git log(SKILL.md). - Boundary markers: Not explicitly defined for the prompt construction.
- Capability inventory: Limited to standard git read commands (
git log,git describe,git tag). No network operations, file writes, or dynamic execution patterns were detected. - Sanitization: The instructions provide guidelines for identifying user-visible changes, which acts as a manual filtering step.
- [COMMAND_EXECUTION]: The skill uses standard git commands to fetch information from the local repository. These commands are non-destructive and strictly related to the skill's primary purpose of changelog generation.
Audit Metadata