welly

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external LAS files, creating an ingestion point for potentially untrusted data that could contain malicious instructions.
  • Ingestion points: Data is loaded from external files using Well.from_las and Project.from_las in scripts/well_qc.py, scripts/project_stats.py, and referenced documentation.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to disregard potential commands embedded within the processed well data or headers.
  • Capability inventory: The toolset includes file-writing capabilities (to_las, to_csv), which could be leveraged if an agent is successfully influenced by injected content.
  • Sanitization: No content sanitization or adversarial pattern filtering is performed on the ingested text data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 11:56 AM
Security Audit — agent-trust-hub — welly