patient-education-readability-review

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which is an inherent characteristic of its intended functionality.
  • Ingestion points: The skill accepts data via patientEducationLink (URLs), patientEducationFile (file uploads), and patientEducationText (user-provided text) as defined in references/form-schema.json.
  • Boundary markers: There are no explicit delimiters or instructions provided in the skill files to isolate external content from the agent's core instructions.
  • Capability inventory: The provided Python script scripts/run.py performs network requests to the vendor's API at https://ai-skills.ai. It does not contain file system write operations or subprocess executions.
  • Sanitization: The skill files do not implement content sanitization or validation for the ingested external data.
  • [EXTERNAL_DOWNLOADS]: The scripts/run.py script makes network calls to https://ai-skills.ai. This domain is the official platform for the skill and represents legitimate communication with the vendor's infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:58 AM
Security Audit — agent-trust-hub — patient-education-readability-review