recherche-doctrine

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with several well-known academic and research platforms, including ISIDORE (CNRS), HAL (French open archive), OpenAlex, Semantic Scholar, CrossRef, and Persée, to fetch legal doctrine and citations.
  • [SAFE]: The instructions include a critical section on bibliographic integrity, explicitly forbidding the AI agent from inventing or extrapolating metadata such as volume numbers or page ranges.
  • [COMMAND_EXECUTION]: Employs standard curl commands to query public academic APIs for legal research purposes; these network operations are directed at established research institutions and are consistent with the skill's primary function.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was detected within the skill instructions or reference documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:33 PM
Security Audit — agent-trust-hub — recherche-doctrine