create-vlog-script
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, which could potentially contain malicious instructions.
- Ingestion points: The instructions require transcribing "rough spoken notes" and performing "research and article captures" from external primary sources (SKILL.md).
- Boundary markers: The skill does not define clear delimiters or "ignore instructions" wrappers for the content retrieved from external articles or voice notes.
- Capability inventory: The agent has the ability to inventory and rename files in a media folder and generate interactive HTML slide guides (SKILL.md).
- Sanitization: There are no instructions for sanitizing or escaping content from external articles before it is interpolated into the final narration or slide guide.
- [DYNAMIC_EXECUTION]: The skill generates interactive code for a presentation-oriented slide guide.
- Evidence: The skill mandates the delivery of an "HTML slide guide" that must support "forward/back navigation by keyboard, click, and a visible slide counter" and include a "full-screen shortcut" (SKILL.md). This requires the agent to generate client-side scripts (JavaScript) to facilitate the UI functionality.
Audit Metadata