secure-mcp-install
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill's examples show embedding an API_KEY value directly in the JSON passed to the CLI (e.g., "API_KEY": "your-key"), which encourages or requires the agent to insert secret values verbatim into generated commands/configs, creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly clones and audits arbitrary third‑party repositories (see "git clone <REPO_URL>" in SKILL.md) and runs scripts that scan and read source files (scripts/audit-mcp-server.sh and the manual audit checklist), so the agent ingests and interprets untrusted, user‑generated content from public repos.
Audit Metadata