guided-learning

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill serves as a set of instructional guidelines for an agent to manage a learning environment. It does not contain any executable scripts, remote code execution, or network exfiltration patterns.- [DATA_EXPOSURE]: The skill operates on local files within a dedicated workspace (e.g., MISSION.md, lessons/, learning-records/). This is consistent with its stated purpose of maintaining stateful learning progress and does not involve accessing sensitive system directories or credentials.- [PROMPT_INJECTION]: The instructions do not contain any attempt to bypass safety guidelines, override system prompts, or extract internal model instructions. It uses natural instructional language to guide the agent's behavior.- [INDIRECT_PROMPT_INJECTION]: While the skill processes external information to create lessons, it emphasizes using "trusted primary sources" and maintains clear boundaries for how data should be formatted and recorded. The risk of indirect injection from teaching materials is minimal and addressed by the structured workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:17 PM