skills/bjornmelin/dev-skills/gsap/Gen Agent Trust Hub

gsap

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user descriptions to generate animation code, providing a surface for indirect prompt injection. 1. Ingestion points: User animation requirements in SKILL.md and references/recipes.md. 2. Boundary markers: Absent; no delimiters are used to separate user input from the prompt logic. 3. Capability inventory: The skill generates JavaScript code and provides a local project auditing CLI. 4. Sanitization: Absent; no specific instructions are provided to sanitize user-provided text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:39 PM
Security Audit — agent-trust-hub — gsap