Audit MCP servers for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure using Invariant Labs' mcp-scan for static/runtime scanning plus manual SSRF/auth checks and description pinning. Use before adding a new MCP server to an agent stack, when reviewing an internal MCP server, detecting rug pulls, or investigating an agent's unexpected tool-driven behavior.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The agent connects to external MCP servers to enumerate tools and read their descriptions, which can contain outsider-authored text (tool poisoning risk).
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The script fetches and executes an installation script from astral.sh (`curl -LsSf https://astral.sh/uv/install.sh | sh`) at runtime without strong first-party verification.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.