od-prototype-data-report
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 placeholder and incorporates it into a brief that determines subsequent agent actions and tool parameters.
- Ingestion points: The $ARGUMENTS variable in SKILL.md receives untrusted input from the user.
- Boundary markers: No specific delimiters or instructions are used to isolate the user input from the skill's logic.
- Capability inventory: The agent is instructed to use open-design MCP tools (prepare_open_design_brief, list_open_design_design_systems, recommend_open_design_design_systems, register_open_design_artifact) and local file-editing tools.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the input before it is used in tool calls or file authorship.
Audit Metadata