youtube-to-blog
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, untrusted content from YouTube transcripts or video URLs.
- Ingestion points: The 'Get the transcript' section in
SKILL.mdidentifies video URLs and transcripts as primary inputs. - Boundary markers: No explicit delimiters (e.g., XML tags or specific markdown blocks) or 'ignore embedded instructions' directives are used when processing the transcript content.
- Capability inventory: The skill possesses the ability to write to files and invoke other internal skills (
article,humanize,internal-links,meta). - Sanitization: There are no instructions to sanitize, escape, or validate the transcript content before it is processed by the agent's logic.
Audit Metadata