seedance-course-promo

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions and templates for generating text prompts. It does not include any scripts, executable files, or command-line operations.
  • [SAFE]: No security issues were detected. The skill generates promotional content for video production and does not access sensitive data or perform network operations.
  • [SAFE]: Indirect Prompt Injection analysis:
  • Ingestion points: User-provided course details, asset descriptions, and call-to-action text are used to fill prompt templates.
  • Boundary markers: The templates use clear structural headers (HOOK, TENSION, EVIDENCE, etc.) to separate different parts of the generated prompt.
  • Capability inventory: No capabilities detected; the skill only generates text and does not interact with the file system, network, or subprocesses.
  • Sanitization: No specific sanitization or escaping of user input is performed, but as the skill lacks exploitable capabilities, this presents no significant risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 08:18 AM
Security Audit — agent-trust-hub — seedance-course-promo