jf-identification

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze manuscript content and empirical research designs, creating a surface for indirect prompt injection where malicious instructions embedded in a paper could influence the agent's behavior.
  • Ingestion points: The skill analyzes manuscript content and user-provided research designs described in the context of the skill execution.
  • Boundary markers: The instructions do not define specific delimiters to separate user data from instructions, nor do they include warnings to ignore embedded commands.
  • Capability inventory: The skill utilizes an execution bridge (StatsPAI / Stata MCP) to run specific statistical commands like detect_design, estimate, and audit_result based on the analyzed content.
  • Sanitization: There is no evidence of sanitization or filtering of the manuscript content before it is processed by the agent or used to parameterize tool calls.
  • [COMMAND_EXECUTION]: The skill guides the agent to use a statistical execution bridge (StatsPAI / Stata MCP) to run estimators and diagnostic tests. This is the primary intended functionality of the skill for empirical research and uses a controlled set of specialized tools rather than arbitrary shell access.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 09:00 PM
Security Audit — agent-trust-hub — jf-identification