regxa-ai-tool

Warn

Audited by Snyk on Mar 13, 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's regxa packageTool (described in SKILL.md Step 3) explicitly fetches package metadata, versions, dependencies, and maintainers from public registries (npm, PyPI, crates.io, RubyGems, Packagist, Arch), which are untrusted user-controlled sources that the agent ingests and can use to drive decisions or actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 07:19 PM
Issues
1