sf-datacloud

Warn

Audited by Snyk on Mar 22, 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 explicitly fetches and uses a public GitHub community plugin (see scripts/bootstrap-plugin.sh and references/plugin-setup.md which clone https://github.com/gthoppae/sf-cli-plugin-data360.git), and then runs/parses that plugin's sf data360 command outputs (scripts/diagnose-org.mjs, scripts/verify-plugin.sh) as part of the required workflow, so untrusted third‑party code/output can influence tool behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill's bootstrap and manual setup explicitly clone and build the external CLI plugin from https://github.com/gthoppae/sf-cli-plugin-data360.git (via scripts/bootstrap-plugin.sh and git clone), which fetches, installs, compiles, links, and enables remote code that the skill requires at runtime—so this URL delivers and executes code the runtime depends on.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 09:20 PM
Issues
2