sales-clari-copilot

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill uses references/learnings.md to store and retrieve accumulated knowledge, creating an indirect prompt injection surface where external data could be persisted and re-ingested. 1. Ingestion points: references/learnings.md (read during Step 1). 2. Boundary markers: Absent. 3. Capability inventory: File read and write access to the references/ directory. 4. Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill mentions installing related tools from the same author (sales-skills) using the npx package runner.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 06:35 PM