od-video-frame-flowchart-sticky
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input through the '$ARGUMENTS' variable and interpolates it into a design brief that is then used by the 'prepare_open_design_brief' tool to generate file-editing instructions for the agent.
- Ingestion points: The '$ARGUMENTS' variable in the skill's instructions.
- Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded within the interpolated user input.
- Capability inventory: The agent uses file-editing tools and various MCP tools ('prepare_open_design_brief', 'list_open_design_design_systems', 'recommend_open_design_design_systems', 'register_open_design_artifact') based on the generated instructions.
- Sanitization: There is no evidence of input validation, sanitization, or escaping of the user-provided data before it is passed to the design tools.
Audit Metadata