assess-current-knowledge

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied context or topics, which creates a surface for indirect prompt injection where malicious instructions could be embedded in the analyzed data.\n
  • Ingestion points: Untrusted data enters the context through the <context or topic> argument in the usage pattern defined in README.md.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the SKILL.md body.\n
  • Capability inventory: The instructions in SKILL.md suggest examining configuration files and experiments for behavior, which implies the use of file system and shell tools available to the agent context.\n
  • Sanitization: No explicit sanitization or validation of the input context is performed by the skill instructions.\n- [EXTERNAL_DOWNLOADS]: The README.md provides instructions to install the skill and download a packaged file from the author's GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 05:24 PM
Security Audit — agent-trust-hub — assess-current-knowledge