perplexity

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly states the skill "reads the web for you" via the Perplexity MCP and returns synthesized answers with inline citations (see "it reads the web for you" and the example "citations" array with "url" in SKILL.md), meaning the agent ingests and acts on untrusted public web content that could carry indirect prompt-injection instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 03:25 PM