ask-explaining-code
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (INFO): The skill is designed to ingest and process user-provided code, which is an inherent attack surface for indirect prompt injection. Evidence: 1. Ingestion points: Code input via triggers in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Text generation and display only; no subprocess or network calls. 4. Sanitization: Not present. Severity is INFO as the skill has no side-effect capabilities.
- [Data Exfiltration] (SAFE): No mechanisms for external data transmission or access to sensitive credentials or files were found.
- [Remote Code Execution] (SAFE): No remote dependencies are downloaded or executed; the included python script is a benign placeholder.
Audit Metadata