ai-claim-checker

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, such as obfuscation, data exfiltration, or remote code execution, were detected. The skill's functionality is limited to prompt-based educational interactions.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it interpolates user-provided content into the agent's prompt for evaluation.
  • Ingestion points: The ai_generated_content parameter in the SKILL.md input schema accepts external text for processing.
  • Boundary markers: Absent; the content is placed directly after a label without protective delimiters or explicit instructions to ignore embedded directives.
  • Capability inventory: The skill defines no allowed tools and contains no scripts for file system access, network communication, or code execution.
  • Sanitization: No input validation or escaping is performed on the content before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 11:56 AM
Security Audit — agent-trust-hub — ai-claim-checker