Skills
Navigate
skills/ai-orchestrators/video-editing-suite/short-form-cut-finder/Gen Agent Trust Hub

short-form-cut-finder

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze long transcripts provided by users, which could contain hidden malicious instructions intended to subvert the agent's behavior.
  • Ingestion points: Long-form transcripts pasted by the user for clip mining (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific warnings for the agent to ignore instructions embedded within the transcript data.
  • Capability inventory: The skill uses the Bash tool and has file system access via Read, Write, and Edit (SKILL.md).
  • Sanitization: No sanitization or escaping of the input transcript is mentioned before the agent processes and extracts content.
  • [COMMAND_EXECUTION]: The skill workflow relies on the Bash tool and references a setup process involving an install.sh script and a cloned repository (video-editing-suite). These tools facilitate system-level command execution to manage configurations and run external utilities like generate_clips.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 01:34 PM