community-post

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes potentially untrusted data from local project files, creating an indirect prompt injection surface.\n
  • Ingestion points: The skill reads video titles, topics, and context from local 'plan.md' files within the './youtube/episode/' directory structure.\n
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands when passing the ingested content to the research and writing foundation skills.\n
  • Capability inventory: The skill has the capability to write and append generated content to local 'community-posts.md' files based on the ingested context.\n
  • Sanitization: No sanitization, validation, or filtering is performed on the data read from the file system before it is interpolated into subsequent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 01:33 AM