video-resolution-upscale

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill frontmatter declares a requirement to read ~/.meitu/credentials.json, which is used to store sensitive API credentials for the Meitu platform.
  • [COMMAND_EXECUTION]: The meitu binary is executed with user-supplied parameters (video_url and target_resolution) interpolated directly into the command string.
  • [COMMAND_EXECUTION]: Indirect Prompt Injection Surface:
  • Ingestion points: The video_url and target_resolution are taken from user input in SKILL.md.
  • Boundary markers: None identified in the provided command template.
  • Capability inventory: The skill has exec permissions for the meitu binary.
  • Sanitization: There is no evidence of input validation or shell escaping for the video_url variable before it is used in a shell execution context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:03 AM
Security Audit — agent-trust-hub — video-resolution-upscale