oc-thumbnail-artist

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute the 'oc' CLI for media processing tasks, which is consistent with its stated purpose of thumbnail generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external video project data and captions, which are interpolated into command arguments. This presents a potential surface for indirect injection from untrusted source content, although the risk is minimized by the specific application domain.
  • Ingestion points: Video project metadata, hook captions, and steering directives.
  • Boundary markers: The instructions lack explicit delimiters or safety headers for the interpolated data.
  • Capability inventory: The skill has the ability to execute shell commands via the Bash tool.
  • Sanitization: No explicit input sanitization or validation logic is defined for the command parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:34 PM
Security Audit — agent-trust-hub — oc-thumbnail-artist