yuque-group-weekly-report
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Yuque API endpoints and interpolates it into a markdown report. This creates a vulnerability surface where malicious content stored in Yuque metadata (such as document titles or member names) could influence the agent's behavior during report generation.
- Ingestion points: The skill retrieves untrusted data from the Yuque platform using
yuque_group_doc_stats,yuque_group_member_stats, andyuque_list_reposin Step 2. - Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to disregard potential commands or adversarial instructions that might be embedded within the documentation activity data.
- Capability inventory: The skill has the capability to write data back to the environment using
yuque_create_docin Step 5. - Sanitization: The workflow lacks explicit sanitization, filtering, or validation steps for the content retrieved from Yuque before it is used to populate the report template in Step 4.
Audit Metadata