add-ollama-tool
Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.
61
71%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/add-ollama-tool/SKILL.mdSecurity
1 medium severity finding. This skill can be installed but you should review these findings before use.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly exposes management tools (pull, delete) that let the agent download or remove models on the host and instructs how to enable them (setting OLLAMA_ADMIN_TOOLS), plus it copies and registers code into the runner—allowing the agent to modify host state though not requesting sudo or creating users.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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 skill exposes only a local Ollama MCP server whose tools send agent-provided prompts to the host Ollama daemon, but it does not ingest any outsider-authored free text from an external queue/feed/inbox/Web page at runtime unless the agent explicitly calls the MCP tool with that text.
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 MCP server code (ollama-mcp-stdio.ts) makes runtime HTTP calls to the Ollama daemon at http://host.docker.internal:11434 (OLLAMA_HOST) — invoking /api/generate and other endpoints — which executes model inference on the host and directly affects agent outputs.
- Repository
- nanocoai/nanoclaw
- Commit
858421a
- 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.