skills/sales-skills/sales/sales-avoma/Gen Agent Trust Hub

sales-avoma

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a persistent state pattern where the agent reads from and writes to 'references/learnings.md' across different sessions. This creates a surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read 'references/learnings.md' at the start of every invocation to retrieve 'accumulated knowledge'.
  • Boundary markers: There are no delimiters or instructions to treat the contents of the learnings file as potentially untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill possesses orchestration capabilities, such as routing to other skills (e.g., '/sales-note-taker'), and provides guidance on utilizing APIs and webhooks.
  • Sanitization: There is no mechanism described for validating or sanitizing the 'gotchas' or 'tips' before the agent appends them to the persistent storage.
  • [EXTERNAL_DOWNLOADS]: The documentation includes instructions for the user to run 'npx skills add sales-skills/sales --skill sales-do'. This command fetches and executes code from the vendor's ('sales-skills') own ecosystem to install related tools and capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 06:34 PM