story-character-sheet

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied character descriptions to generate structured visual sheets, which are then passed to downstream skills. 1. Ingestion points: User character visual descriptions. 2. Boundary markers: The skill's output format lacks explicit delimiters or markers to isolate user-provided data from system instructions. 3. Capability inventory: The skill itself contains no internal scripting or execution capabilities, but its output influences the art generation and quality control processes of other agent skills. 4. Sanitization: No input validation or character filtering is performed on user descriptions.
  • [SAFE]: The skill refers to Higgsfield.ai (https://higgsfield.ai), which is a well-known AI video and image generation service, as a fallback resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — story-character-sheet