Skills
skills/pauljbernard/content/curriculum-review-accessibility/Gen Agent Trust Hub

curriculum-review-accessibility

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill identifies a surface for indirect prompt injection because its primary function is to ingest and analyze untrusted external data (curriculum materials).
  • Ingestion points: The content_path parameter in skill.py and the Materials input described in SKILL.md.
  • Boundary markers: None identified; the skill does not currently provide delimiters or instructions to the agent to ignore embedded commands within the materials.
  • Capability inventory: The provided skill.py is a stub that returns hardcoded status data and does not currently perform file system writes, network requests, or subprocess execution.
  • Sanitization: No sanitization or validation logic is present to filter malicious instructions within the processed documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM