deliver-release-notes
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface for untrusted data by directing the agent to work from engineering changelogs, completed tickets, and pull request descriptions.
- Ingestion points: Defined in SKILL.md (Step 1) and utilized in the evaluation scenarios (evals/output-scenarios/).
- Boundary markers: The instructions do not prescribe the use of delimiters or specific warnings to ignore embedded instructions within the source data.
- Capability inventory: The skill is purely text-based and does not employ any tools for file writing, network communication, or system command execution.
- Sanitization: No automated sanitization is specified, although the instructions for benefit-focused rewriting provide a layer of content transformation.
Audit Metadata