academic-research

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • PROMPT_INJECTION (MEDIUM): The skill is susceptible to indirect prompt injection because it ingests and synthesizes untrusted content from the web and academic databases. Ingestion points: Untrusted data enters the agent context through search result snippets and the classify-url tool in scripts/research_agent.py. Boundary markers: No markers or 'ignore' instructions are provided to the model to delineate untrusted external content. Capability inventory: The skill performs network searches and generates structured research reports, which could be subverted by malicious content. Sanitization: No filtering or sanitization of retrieved content is described.
  • COMMAND_EXECUTION (LOW): The skill executes a local Python script scripts/research_agent.py to perform query generation and URL classification. While typical for skill functionality, it provides an execution path for logic processing potentially untrusted data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 12:19 AM