cli-anything-quietshrink

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (github.com/achiya-automation/quietshrink) and an associated installation script as the source for the cli-anything-quietshrink utility.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The agent processes external video files through the compress and probe commands defined in SKILL.md.
  • Boundary markers: Absent. The skill instructions do not specify delimiters for untrusted file metadata or provide 'ignore embedded instructions' warnings.
  • Capability inventory: The skill performs shell execution of the cli-anything-quietshrink tool (via SKILL.md).
  • Sanitization: Absent. No input validation or output escaping is described for the data processed from the video files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:21 PM
Security Audit — agent-trust-hub — cli-anything-quietshrink