Skills
Navigate
skills/feimacode/open-design-agent-kit/od-prototype-social-spotify-card/Gen Agent Trust Hub

od-prototype-social-spotify-card

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 and interpolate it into a prompt brief for file creation and tool execution.
  • Ingestion points: The $ARGUMENTS placeholder in SKILL.md captures raw user input.
  • Boundary markers: The input is wrapped in double quotes within the text of the brief, but there are no explicit safety delimiters or instructions for the agent to ignore potentially malicious embedded content.
  • Capability inventory: The skill allows the agent to use file-editing tools to author code and call the register_open_design_artifact tool.
  • Sanitization: No sanitization, escaping, or validation of the $ARGUMENTS content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 03:37 PM