prompt-preflight-qa
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions for a Quality Assurance workflow. It does not include any scripts, executable content, or remote dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied prompt drafts for video requests.
- Ingestion points: User-provided prompt objects and video requests processed in the "Default Workflow" section of SKILL.md.
- Boundary markers: None defined in the instructions.
- Capability inventory: No file system access, network operations, subprocess execution, or dynamic code execution capabilities are defined or requested in this skill.
- Sanitization: No input sanitization or escaping mechanisms are described.
- Result: While the skill handles untrusted external data, the total lack of side-effect capabilities renders the attack surface non-exploitable.
Audit Metadata