skills/arcads-ai/skills/animated-ad/Gen Agent Trust Hub

animated-ad

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied data which is then used to generate prompts for other tools, creating a surface for indirect instructions to influence agent behavior.
  • Ingestion points: According to SKILL.md, the skill takes a "product, offer, or raw ad script" or "pasted product/offer" provided by the user as primary input for ad generation.
  • Boundary markers: The skill instructions do not include explicit delimiters or "ignore embedded instructions" warnings for the user-provided text when it is processed by the agent.
  • Capability inventory: The skill has access to and generates content for the arcads_generate_video_seedance_20, arcads_generate_image, and arcads_text_to_speech tools.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the user-provided script or product text before it is interpolated into the complex and simple workflow prompt templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 01:28 AM