Skills
Navigate
skills/feimacode/open-design-agent-kit/od-deck-deck-swiss-international/Gen Agent Trust Hub

od-deck-deck-swiss-international

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill uses the $ARGUMENTS variable to ingest user input, which is then interpolated directly into a brief for the prepare_open_design_brief tool.
  • Ingestion points: The $ARGUMENTS variable in SKILL.md captures user input.
  • Boundary markers: There are no explicit delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings surrounding the interpolated input.
  • Capability inventory: The skill calls MCP tools (prepare_open_design_brief, register_open_design_artifact) and instructs the agent to author files using file-editing tools.
  • Sanitization: No sanitization, validation, or escaping of the user-provided content is performed before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 03:37 PM