lead-intelligence

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources and uses it to drive agent behavior.
  • Ingestion points: Public profile data, recent posts, and company news are fetched from the X API, LinkedIn (via browser/cookies), GitHub, and Exa web search (enrichment-agent.md, signal-scorer.md).
  • Boundary markers: The agent instructions for the outreach-drafter and enrichment-agent lack explicit delimiters or instructions to ignore potential commands embedded in the fetched profile content.
  • Capability inventory: The skill possesses the ability to create email drafts in the local Apple Mail application and prepare messages on LinkedIn and X via browser control or API (SKILL.md). Agents also have access to the Bash tool for local operations.
  • Sanitization: There is no evidence of sanitization or escaping of the external content before it is interpolated into the generation prompts for outreach messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 04:01 AM
Security Audit — agent-trust-hub — lead-intelligence