screencast-publish
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides high-level instructions and a checklist for video publishing workflows. It does not include any executable code, scripts, or automated network operations.
- [INDIRECT_PROMPT_INJECTION]: The workflow involves the agent inspecting external assets and URLs, which represents a potential ingestion surface for untrusted data.
- Ingestion points: The agent is instructed to inspect metadata, screenshots, URLs, and files as defined in SKILL.md.
- Boundary markers: The skill does not define specific delimiters for separating untrusted content from instructions during the inspection process.
- Capability inventory: The instructions involve performing export, upload, and access checks using external tools when permissions permit.
- Sanitization: There are no instructions for sanitizing or validating external content before it is processed by the agent.
Audit Metadata