customer-persona

Fail

Audited by Snyk on Feb 19, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). The three URLs point to a small/unknown domain that serves a remote install script (curl | sh) and downloadable binaries with checksums hosted on the same domain — executing a remote .sh or downloaded executables without independent signatures is a high-risk vector for malware or supply-chain compromise.

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md "Step 1: Research" explicitly instructs running commands like infsh app run tavily/search-assistant and infsh app run exa/search to query public web/search results, which the agent is expected to read and use to build personas—so untrusted third‑party content can materially influence subsequent decisions and actions.

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

  • Potentially malicious external URL detected (high risk: 1.00). The Quick Start explicitly instructs running "curl -fsSL https://cli.inference.sh | sh" (which downloads and executes a remote installer and retrieves binaries from dist.inference.sh) and the skill's examples rely on that CLI at runtime, so this URL is a required runtime dependency that executes remote code.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 19, 2026, 08:05 PM