horror-suspense-short

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references numerous external URLs in references/cases.md for video examples, posters, and source content hosted on goodcase.ai, media.goodcase.ai, and x.com. These are third-party domains used to provide visual references for the prompt generation workflow.
  • [INDIRECT_PROMPT_INJECTION]: The workflow requires the agent to fetch and inspect external media assets to derive structural traits and visual styles. This ingestion of untrusted external data creates a vulnerability surface where crafted media could attempt to influence the agent's behavior or output.
  • Ingestion points: External media and case links found in references/cases.md.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat the external media as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill utilizes image, video, and browser tools to access and analyze the external references.
  • Sanitization: No sanitization or validation of the external content is performed before it is incorporated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 11:02 PM