release-notes-one-pager
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions designed to influence the agent's behavior or inject malicious content into the generated HTML. While the skill includes instructions for 'honesty' and accuracy, it lacks explicit boundary markers or sanitization steps for the ingested data.
- Ingestion points: The skill ingests user-provided text (release notes, changelogs) and reads an external workspace file named
DESIGN.mdto map variables (Step 0). - Boundary markers: There are no instructions to wrap external content in delimiters or use explicit warnings to ignore embedded instructions within the source material.
- Capability inventory: The skill is capable of generating HTML artifacts containing CSS and JavaScript (via
assets/template.htmlandexample.html). - Sanitization: The instructions do not explicitly mandate HTML entity encoding, input validation, or escaping of user-provided content before interpolation into the final document.
Audit Metadata