3d-cartoon-character-short-by-18gc2qf
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external prompt excerpts and media descriptions.\n
- Ingestion points: The
references/cases.mdfile contains prompt excerpts and summaries from the GoodCase.ai platform.\n - Boundary markers: The skill lacks explicit instructions for the agent to ignore any embedded directives within the analyzed prompts.\n
- Capability inventory: The skill utilizes image, video, or browser tools to inspect media content referred to in the external data.\n
- Sanitization: There is no evidence of sanitization or filtering of external content before processing.\n- [EXTERNAL_DOWNLOADS]: The skill references and instructs the agent to inspect media and data from external domains.\n
- Sources: GoodCase.ai (
goodcase.ai,media.goodcase.ai) and X/Twitter (x.com).\n - Use Case: These are used as primary reference sources for the skill's intended functionality.
Audit Metadata