release
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from TASKS.md and individual task documents which are potentially untrusted or external inputs.
- Ingestion points: The workflow reads TASKS.md and individual task documents in steps 2 and 3 to generate changelogs and release notes.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the task data when generating the changelog.
- Capability inventory: The skill has file-write capabilities for updating CHANGELOG.md and TASKS.md, and command execution capabilities for git operations (commit, tag).
- Sanitization: No explicit sanitization or validation of the user-provided task summaries is performed before they are interpolated into the changelog template.
Audit Metadata