boring-video

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external articles and research bundles to drive the video production chain, creating a surface where malicious instructions in the source text could influence agent behavior.
  • Ingestion points: content/ARTICLE.md and content/RESEARCH.md are populated from external URLs or paths.
  • Boundary markers: While the skill uses YAML frontmatter and SHA-256 digests for versioning and integrity, it does not specify clear delimiters or ignore instructions for the content body.
  • Capability inventory: The skill manages a chain of tools for narration, scene rendering, and video production based on the ingested content.
  • Sanitization: No explicit sanitization or validation of the external text content is mentioned before it is passed to downstream skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 08:16 AM