jianying-draft-filters
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests and processes untrusted external data to drive its filter management operations.
- Ingestion points: Creative briefs ('创作简报') and user-supplied keywords are used to search and select filters, as detailed in SKILL.md and references/workflow.md.
- Boundary markers: There are no explicit delimiters or specific instructions to the agent to disregard commands embedded within the creative briefs or metadata.
- Capability inventory: The skill possesses the ability to modify video draft timelines via 'timeline add-filter' and 'timeline remove' commands and to download official resources through a specialized adapter.
- Sanitization: No input validation, escaping, or filtering mechanisms are described for the content derived from the creative briefs before it is used in tool parameters.
Audit Metadata