analog-occultism

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of markdown-based creative templates and aesthetic guidelines. It does not include any scripts, executables, or instructions that interact with the underlying system or network.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use FFmpeg or FFprobe to verify video metadata and frames. This is a standard use of media analysis tools within the agent's environment for quality assurance and does not present an arbitrary command execution risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill templates ingest a user-defined subject. This ingestion surface is used exclusively for visual rendering within a constrained creative framework. There are no high-risk capabilities associated with this input, and the templates provide clear structure for the resulting prompt.
  • [METADATA_POISONING]: The frontmatter and README metadata accurately describe the skill's visual purpose and technical requirements without deceptive or misleading instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 11:23 PM
Security Audit — agent-trust-hub — analog-occultism