mcp-cli
Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations
56
63%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/mcp-cli/SKILL.mdW007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill includes concrete examples that embed credentials directly in commands (e.g., --auth-user "username:password", --auth-header "Bearer your-token-here", export GITHUB_PERSONAL_ACCESS_TOKEN, docker -e), which would require an LLM or user to place secret values verbatim into generated commands — an insecure pattern that risks secret exfiltration.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The runtime workflow is the `mcp` CLI invoking MCP servers via commands like `mcp tools/resources/prompts` and reading a `resource-uri` (`mcp read-resource <resource-uri> ...`), so outsider-authored free text can be ingested whenever a user selects a server/resource that itself returns externally authored content (e.g., HTTP/SSE or community-provided MCP servers) without any filtering at the skill level.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
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.
Why it was flagged
The skill's setup instructs cloning and building remote code from https://github.com/f/mcptools.git (git clone + go build), which fetches and executes external code required to install the mcp CLI.
- Repository
- obra/superpowers-lab
- Commit
51111f7
- Audited
- Security analysis
Is this your skill?
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.