sales-manager

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions reference a skill builder repository located at github.com/peter-tu-zynkr/zynkr-skill-builder. This reference targets the author's own namespace for development tooling purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions as a conductor for processing various external sales signals, creating a surface for indirect instructions to potentially influence the agent.
  • Ingestion points: Data is ingested from business card OCR results, event survey sheets, and discovery call transcripts as described in the ROUTE and SEQUENCE workflows in SKILL.md.
  • Boundary markers: The instructions do not specify technical delimiters (such as XML tags or boundary markers) for external content, although they define a structural safety gate for write operations.
  • Capability inventory: The agent has the ability to modify CRM data (deals, tasks, contacts) using the zynkr toolset (move_deal_stage, update_deal, etc.) as detailed in the Fixed Facts section of SKILL.md.
  • Sanitization: No programmatic sanitization of external inputs is documented; the primary mitigation is the mandatory human confirmation required for all proposed batch write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:31 PM
Security Audit — agent-trust-hub — sales-manager