k2f-intake-form
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to act as a form designer, focusing on semantic content and aesthetic hierarchy.
- [EXTERNAL_DOWNLOADS]: The skill mentions the installation of a core dependency (
suzheng/k2f) via a platform-specific command. As this resource is provided by the same author as the skill, it is considered a vendor-owned resource and does not present a security risk. - [INDIRECT_PROMPT_INJECTION]: While the skill involves processing user-supplied briefs or templates (an ingestion point for potentially untrusted data), it includes strict guidelines such as the 'Truth gate' and 'Consent gate' which explicitly instruct the agent not to guess or fabricate clinical protocols, legal text, or statutory wording. This effectively mitigates the risk of the agent being manipulated into producing unauthorized or unsafe content.
Audit Metadata