evaluate
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is primarily designed to ingest and analyze external data in the form of user experience designs, screenshots, or descriptions provided by the user for audit.
- Ingestion points: The skill processes user-provided designs, audit requests, and experience descriptions as defined in the description and trigger fields (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the evaluated content as untrusted data or to ignore instructions embedded within the designs themselves.
- Capability inventory: The skill defines logic for assessment but does not include scripts that execute subprocesses, write files, or perform network operations. Its capabilities are limited to analytical routing within the Intent system.
- Sanitization: No sanitization, filtering, or validation mechanisms for the input data are described in the instructions.
Audit Metadata