using-openspend-cli

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: 0.90). The skill's required install step (curl -fsSL https://openspend.ai/install | sh shown in SKILL.md and scripts/install.sh) fetches and executes a script from a public third‑party URL, allowing external content to directly control the agent's actions.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime installer that runs remote code via "curl -fsSL https://openspend.ai/install | sh", which fetches and immediately executes code from that URL and is presented as a required installation method.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 06:27 PM