jianying-draft-editing-console
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted project data.
- Ingestion points: The skill reads external project drafts from local paths, as demonstrated in
examples/minimal-job.json(e.g.,/absolute/path/to/console-source-draft). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within project metadata or file content.
- Capability inventory: The skill utilizes powerful capabilities including
timeline.edit,timeline.remove, andruntime.controlswhich can modify or delete project data. - Sanitization: The instructions lack specific requirements for sanitizing or validating the content of the project drafts before executing semantic commands.
Audit Metadata