book-illustration-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
lark-clitool to synchronize content with the Feishu platform, performing actions like document creation and media insertion via the command line. - [INDIRECT_PROMPT_INJECTION]: The skill processes local Markdown files to determine illustration placement and workflow steps, creating a surface where malicious content in those files could influence the agent.
- Ingestion points: The skill reads local Markdown files to identify figure numbers, placeholders, and content structure.
- Boundary markers: No specific delimiters or instructions to ignore embedded instructions are present in the processing logic.
- Capability inventory: The skill has permissions to modify local files and access the network via
lark-clifor Feishu synchronization. - Sanitization: There is no evidence of sanitization or validation of the ingested file content before it is used to drive the workflow.
Audit Metadata