video-ad-specs

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the belt-sh/cli tool via npx and references external documentation and configuration files hosted at raw.githubusercontent.com/inference-sh/skills. These resources are central to the skill's stated purpose of video generation via the inference.sh platform.- [INDIRECT_PROMPT_INJECTION]: The skill provides numerous command-line examples (e.g., in SKILL.md) that interpolate user-provided prompts directly into JSON input objects for the belt CLI. This architecture lacks input sanitization or boundary markers, creating a surface where malicious instructions embedded in processed data could attempt to influence the agent's behavior or the output of the video generation tools.\n
  • Ingestion points: CLI command templates in SKILL.md that accept user-defined --input strings.\n
  • Boundary markers: Absent; user prompts are placed directly inside JSON structures without escaping or delimiters.\n
  • Capability inventory: Execution of the belt CLI tool via shell commands.\n
  • Sanitization: None detected in the provided templates.- [COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of shell commands using the belt CLI tool to interface with remote video generation models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — video-ad-specs