SkillSpector is NVIDIA's Apache-2.0 security scanner for AI agent skills. Point it at a Git repo, URL, zip, folder or single file and it checks for prompt injection, data exfiltration, privilege escalation, supply-chain and MCP tool-poisoning risks, then returns a 0-100 risk score with a recommendation. Static checks run without an LLM; optional semantic analysis uses a model provider you configure. Reports export as terminal, JSON, Markdown or SARIF for CI.
Alternatives to MEDUSA
2 editor-selected alternatives · MEDUSA overview →
source: tools.alternatives · stored order · active records only; review scores are annotations and never change membership or order
A directional evidence panel appears only when the substitute rationale, trade-offs, sources, and verification date have been recorded. Older selections without that panel remain visible but are unclassified under the new evidence contract.
MCP-Scan is a security tool that scans MCP servers for vulnerabilities including tool poisoning, prompt injection, cross-origin escalation, and rug pull attacks. Acquired by Snyk in 2026, it is the first dedicated security scanner for the MCP ecosystem. It analyzes tool descriptions, permissions, and behavior patterns to detect malicious or compromised MCP servers before they can exploit AI agents.
Open-source MEDUSA alternatives
SkillSpector, MCP-Scan — see all open-source developer tools.
More AI Security & DevSecOps tools
same category, not editor-selected alternatives — see how MEDUSA compares →
FAQ
Which MEDUSA alternative is listed first?
SkillSpector is first in the editor-selected list of 2 MEDUSA alternatives. The stored order is editorial; review scores do not determine membership or position.
Are there open-source MEDUSA alternatives?
Yes — SkillSpector, MCP-Scan are open source.