preview

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious code, hardcoded credentials, or exfiltration patterns were detected in the skill instructions.- [COMMAND_EXECUTION]: The skill specifies the use of the open command on macOS to view files locally. This is a standard and safe operation for a preview utility.- [PROMPT_INJECTION]: The skill processes untrusted document data (Markdown, LaTeX) for rendering, which represents an attack surface for indirect prompt injection.
  • Ingestion points: Processes .md, .tex, and .pdf files through rendering commands in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided.
  • Capability inventory: Uses the open command and internal /preview rendering logic described in SKILL.md.
  • Sanitization: No specific sanitization or validation of input content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 05:29 AM
Security Audit — agent-trust-hub — preview