scroll-narrative-copy-pacing

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided copy to calculate pacing constants. If this copy contains malicious instructions, the agent might follow them while processing the text.
  • Ingestion points: The createBeat function in SKILL.md takes a text parameter for word count calculation.
  • Boundary markers: No explicit delimiters are used to wrap the input text.
  • Capability inventory: The skill interacts with the DOM and the GSAP library for animations but does not perform network operations or sensitive file access.
  • Sanitization: Input text is processed for word count but no safety sanitization or instruction-filtering is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 05:48 PM
Security Audit — agent-trust-hub — scroll-narrative-copy-pacing