orbitant-learning-insights
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing unstructured text from previous interactions to build learner context and update insights.
- Ingestion points: Historical lesson data in
~/.claude/learning/lessons/archive/and session logs in~/.claude/learning/logs/(SKILL.md). - Boundary markers: Absent. The instructions do not define explicit delimiters or instructions to ignore embedded commands within the processed log files.
- Capability inventory: The skill performs file-read operations on session history and file-write operations to the persistent
insights.mdfile. - Sanitization: No evidence of sanitization, filtering, or validation of the ingested historical content is mentioned to prevent instruction leakage from past logs into the current session context.
Audit Metadata