muapi-product-ad-cinematic

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network operations using curl and the muapi CLI to communicate with api.muapi.ai. These requests are used to send generation parameters and poll for results from the vendor's API.
  • [PROMPT_INJECTION]: The skill incorporates user-provided text from the brand_brief input directly into prompts for image and audio generation. This represents an indirect prompt injection surface where a malicious input could attempt to influence the output of the generative models.
  • Ingestion points: brand_brief input variable defined in SKILL.md.
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are present in the prompt templates.
  • Capability inventory: The skill invokes muapi CLI commands and curl subprocesses to perform media generation and file operations.
  • Sanitization: The input is interpolated into prompts without explicit validation or escaping of special characters.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:04 PM
Security Audit — agent-trust-hub — muapi-product-ad-cinematic