od-prototype-poster-hero

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements a legitimate workflow for a design-focused AI agent. It interacts with specialized 'Open Design' tools to process design briefs, recommend design systems, and register generated artifacts. All tool calls and logic are consistent with the stated purpose of a marketing poster generator.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingest user input through the $ARGUMENTS variable, which is then used to construct a prompt for the prepare_open_design_brief tool.
  • Ingestion points: User input captured via $ARGUMENTS in SKILL.md.
  • Boundary markers: Absent; the user input is directly inserted into the instruction string.
  • Capability inventory: The agent utilizes prepare_open_design_brief, list_open_design_design_systems, recommend_open_design_design_systems, and register_open_design_artifact tools, in addition to standard file-editing capabilities.
  • Sanitization: There is no explicit sanitization or instruction to ignore embedded commands within the user-provided argument string.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 03:37 PM