jinko-task-extract-data-table

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from external biomedical sources, including papers, images, and web content.
  • Ingestion points: The skill processes external artifacts such as PDF papers, graphical figures, and supplementary tables (SKILL.md).
  • Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to ignore malicious prompts that might be embedded in the source documents.
  • Capability inventory: The skill invokes the jinko-data-table script to perform data validation and server uploads (SKILL.md).
  • Sanitization: Data integrity and schema validation are managed by the jinko-data-table script and the vendor's server-side logic.
  • [COMMAND_EXECUTION]: The skill workflow involves executing a specialized script, jinko-data-table, to perform schema checks and data synchronization.
  • The script execution includes both dry-run modes for validation and active modes for data submission, which are standard operations for the skill's intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 12:26 PM
Security Audit — agent-trust-hub — jinko-task-extract-data-table