binlee-doctor-ip

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for content strategy and professional branding. It operates entirely by reading local markdown files and generating text responses.
  • [DATA_EXPOSURE]: The skill references a local file path ../binlee-source-library/references/evidence-policy.md. This is used to access the specific medical corpus required for the skill's functionality. It does not attempt to access sensitive system files, environment variables, or user credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external local files (evidence-policy.md). While this provides a surface for indirect prompt injection if the source files were compromised, the risk is low given the context of a curated local library for medical branding.
  • Ingestion points: Reads content from ../binlee-source-library/references/evidence-policy.md (SKILL.md).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Only text generation and local file reading are requested.
  • Sanitization: None detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:23 AM
Security Audit — agent-trust-hub — binlee-doctor-ip