teach
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No malicious instructions or bypass attempts identified.
- [Data Exposure] (SAFE): No sensitive file access or credential leaks found.
- [Indirect Prompt Injection] (LOW): The skill includes a template for reading from a progress file (~/.skulto/teach/progress.md). While this is an ingestion surface for untrusted data, the provided files demonstrate no dangerous capabilities that could be exploited. (1) Ingestion points: progress.md; (2) Boundary markers: Absent; (3) Capability inventory: None; (4) Sanitization: Absent.
- [Remote Code Execution] (SAFE): No remote code execution or external downloads were detected.
- [Privilege Escalation] (SAFE): No commands for elevating user privileges were found.
Audit Metadata