press-release-writing

Warn

Audited by Snyk on Mar 10, 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 "Research & Fact-Checking" section explicitly instructs using the inference.sh CLI (e.g., infsh app run tavily/search-assistant, exa/search, exa/answer) to query public web/search apps for statistics and competitor info, which the agent is expected to read and use to shape press-release content—exposing it to untrusted third-party web content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 09:30 PM