learning-mentor
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and synthesize information from external AI sources (e.g., Perplexity). This constitutes an ingestion surface for untrusted data. \n
- Ingestion point: SKILL.md ('Multi-AI Integration' section). \n
- Boundary markers: Absent. \n
- Capability inventory: Limited to reasoning and display of educational content; no subprocess calls, file-write, or network operations found. \n
- Sanitization: None explicitly defined, though it instructs to 'question and validate' external data. \n- [Prompt Injection] (SAFE): No direct instructions to override behavior or bypass safety filters were detected. \n- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths or unauthorized network operations were found. \n- [Remote Code Execution] (SAFE): No remote code downloads or execution patterns were identified. \n- [Obfuscation] (SAFE): No encoded strings or hidden characters were detected.
Audit Metadata