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