human-ui
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches data from
https://guidelines.sh/api/guidelines?type=ui. This domain is not an established trusted organization or well-known service, and fetching instructional content from unverified external sources introduces a supply chain risk for the agent's behavior. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing untrusted data from the network and local files.
- Ingestion points: External API (
guidelines.sh) and user-provided files or directories. - Boundary markers: Absent; the instructions do not implement delimiters or 'ignore embedded instructions' warnings for the fetched guidelines or the files being reviewed.
- Capability inventory: The skill utilizes
WebFetchfor network access and the capability to read local files. - Sanitization: No content validation or sanitization is performed on the retrieved guidelines before they are used to influence the agent's design audit logic.
Audit Metadata