01-blog-to-video

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external content from user-supplied blog posts or URLs, which creates a surface for indirect prompt injection where malicious instructions embedded in the source material could attempt to manipulate the script writing or provider selection process.
  • Ingestion points: The skill ingests 'A published blog post URL, or its draft text/markdown' as defined in the Input section of SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore instructions embedded within the source text during the claim extraction phase.
  • Capability inventory: The agent generates video clips by calling external provider adapters as described in Step 5 of the pipeline.
  • Sanitization: No input validation, filtering, or escaping is applied to the blog content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:36 PM
Security Audit — agent-trust-hub — 01-blog-to-video