competitor-intelligence

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md Analysis Workflow and MCP Tools explicitly fetch and ingest public, user-generated X/Twitter content (e.g., via x_get_tweets, x_get_followers, x_get_profile) and scan bios/tweets as part of decision-making, so untrusted third-party posts could indirectly inject instructions into the agent's analyses and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 09:53 AM