research-fact-checker

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE] (SAFE): No malicious behavior, obfuscation, or data exfiltration patterns were detected. The skill consists purely of markdown-based instructions for an AI agent.
  • [NO_CODE] (INFO): The skill does not contain any scripts, command-line operations, or package dependencies, posing no risk of remote code execution or privilege escalation.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill's primary function is to research and verify external data, which is an inherent ingestion surface. Evidence: 1. Ingestion points: External research sources and websites (implied in the research process). 2. Boundary markers: None specified for external content. 3. Capability inventory: Natural language reasoning, summarization, and reporting; no high-privilege capabilities like file modification or subprocess execution are defined in this skill. 4. Sanitization: No sanitization or filtering of external content is specified. The risk is limited to influencing the agent's internal reasoning.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 12:46 PM