cold-open-creator

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (INFO): The skill processes untrusted external data in the form of podcast transcripts. * Ingestion points: Transcript text processed during clip selection in Step 1. * Boundary markers: Absent; the skill does not instruct the agent to ignore or delimit embedded instructions within transcripts. * Capability inventory: No executable capabilities identified; limited to text output generation. * Sanitization: Absent; the skill requires verbatim extraction.
  • NO_CODE (SAFE): No scripts, binaries, or active code patterns were detected in the skill file.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:38 PM