clay-video-production

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions provide templates for executing shell commands with user-provided arguments, which creates a potential indirect prompt injection surface.
    • Ingestion points: User-controlled placeholders including <client-folder>, video-N, and <photo> are used in project initialization and asset generation commands found in SKILL.md and references/product.md.
    • Boundary markers: Absent. The prompt templates do not include delimiters or specific instructions to isolate or treat user-provided data as untrusted.
    • Capability inventory: The skill relies on shell execution (bash) and Python script execution (make.py) as part of its core functionality for managing video projects.
    • Sanitization: Absent. There are no descriptions of input validation, filtering, or shell-escaping mechanisms for the data interpolated into these command strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 01:59 AM