jianying-draft-recover
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external project drafts, media assets, and task configurations, which constitutes an indirect prompt injection surface.
- Ingestion points: The agent reads from local file paths to access draft data, media files, and task status roots as defined in
SKILL.md(Step 3) andreferences/workflow.md. - Boundary markers: The instructions mandate the use of
project verifyfor structural integrity checks and require explicit user confirmation for high-risk write operations or retries. - Capability inventory: The skill utilizes the
jianyingCLI to perform operations such asjob show,job audit, andstore restore. - Sanitization: The skill implements strict schema validation (specifically
jianying-job/v2) and verifies input/output hashes to prevent the processing of malformed or unauthorized data.
Audit Metadata