skills/q00/openclip/oc-subtitle-agent/Gen Agent Trust Hub

oc-subtitle-agent

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the oc command-line utility via Bash to perform subtitle generation, translation, and video burn-in operations. These commands are project-specific and focused on media processing.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data files (transcript.json) to generate subtitles. This represents a potential attack surface where malicious content within the transcript could attempt to influence the agent's output, particularly during the translation phase.
  • Ingestion points: Reads the <PROJECT>/transcript.json file to extract dialogue and timing information.
  • Boundary markers: None explicitly defined in the instructions for the content of the transcript.
  • Capability inventory: Uses Bash and Read tools to execute oc commands and manage output files.
  • Sanitization: No specific sanitization or filtering of transcript content is described in the markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:34 PM
Security Audit — agent-trust-hub — oc-subtitle-agent