sales-meeting-ai

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a suggested command (npx skills add sales-skills/sales --skill sales-do) in the 'Related skills' section. This is a standard installation instruction for the user to expand their local toolkit using the author's provided package.- [PROMPT_INJECTION]: The skill uses references/learnings.md as a persistent storage for accumulated knowledge. This creates an indirect prompt injection surface where external data could influence the agent's behavior.
  • Ingestion points: The agent reads from references/learnings.md in Step 1 to gather context.
  • Boundary markers: No specific boundary markers or instruction-ignoring warnings are implemented for the content read from the learnings file.
  • Capability inventory: The skill is designed for informational guidance and does not trigger automated subprocesses or network requests based on the contents of the learnings file.
  • Sanitization: There is no evidence of sanitization or validation of the data appended to or read from the learnings file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 08:34 AM
Security Audit — agent-trust-hub — sales-meeting-ai