outreach-personalization-research

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes Amplemarket's MCP tools (enrich_person, enrich_company, search_people) to fetch business data. These are legitimate tool calls associated with the skill's primary function and author.
  • [DATA_EXFILTRATION]: No unauthorized data exfiltration was detected. The skill processes person and company data provided by the user or fetched through authorized vendor APIs to generate a local brief. It does not attempt to send this data to untrusted third-party domains.
  • [COMMAND_EXECUTION]: The skill contains no executable scripts, shell commands, or subprocess calls. All operations are conducted via high-level tool invocations and natural language reasoning.
  • [PROMPT_INJECTION]: The instructions are focused on the intended task. There are no attempts to bypass safety filters, ignore previous instructions, or extract system prompts.
  • [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or other credentials are present in the skill files. It appropriately relies on the MCP environment for tool authentication.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 11:36 PM
Security Audit — agent-trust-hub — outreach-personalization-research