distribution-lead

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted external data, specifically video transcripts and user comments, to automate the creation of social media posts and reply drafts. This presents an indirect prompt injection surface where instructions hidden in the data could influence the agent's behavior.
  • Ingestion points: Video transcripts processed by 'yt-shorts' and audience comments handled by 'yt-comment' as described in sections 3 and 6.
  • Boundary markers: Absent; the skill lacks specific delimiters or system-level instructions to ignore potential commands embedded within the external text.
  • Capability inventory: High-impact capabilities include the ability to post to social media via 'x-posting' and draft communications via 'email-writing'.
  • Sanitization: Absent; there are no instructions to sanitize or validate external content before it is interpolated into prompts or used for outgoing messages.
  • [COMMAND_EXECUTION]: The skill uses the 'ffprobe' command-line utility to extract and verify media metadata (resolution, frame rate, duration, and audio presence) for generated video files to ensure they meet platform requirements before publishing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 04:51 PM