frame-data-chart-nyt
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill configuration and instructions do not contain any malicious patterns. The use of a restricted invocation policy in the agent settings is a security best practice that reduces the risk of unintended tool usage.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input messages to construct design briefs, which are then passed to external design tools. Ingestion points: The skill body in SKILL.md indicates that the user's message is treated as the brief. Boundary markers: No specific delimiters or safety warnings are used to isolate the user-provided message content. Capability inventory: The skill utilizes MCP tools (prepare_open_design_brief, register_open_design_artifact) and the agent's internal file-authoring capabilities. Sanitization: There is no explicit sanitization step for the user input before it is interpolated into the brief tool call.
Audit Metadata