performance-memo

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill is designed to handle sensitive business data from sources like Stripe, HubSpot, and various advertising platforms. Accessing this data is essential for its primary function of performance analysis and decision-making.
  • [COMMAND_EXECUTION]: It utilizes a large set of specialized MCP tools (e.g., mcp__cogny__mcp__Google_Ads__tool_execute_gaql, mcp__cogny__mcp__Stripe__stripe_api_read) to interact with external APIs. These interactions are scoped to the allowed-tools configuration and the vendor's infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: As the skill processes data from diverse external platforms (such as campaign names or CRM deal descriptions), there is a potential surface for indirect prompt injection. The skill relies on the underlying agent's guardrails to handle any malicious instructions embedded in this external data during analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 06:43 PM