add-atomic-chat-tool
Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.
64
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/add-atomic-chat-tool/SKILL.mdLow
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
In `atomic-chat-mcp-stdio.ts`, the MCP tool `atomic_chat_list_models` and `atomic_chat_generate` directly fetch and ingest free-text responses from the (user-configurable) local Atomic Chat OpenAI-compatible endpoints (`${ATOMIC_CHAT_HOST}/v1/models` and `${ATOMIC_CHAT_HOST}/v1/chat/completions`), and `atomic_chat_generate` builds messages from outsider-provided `prompt`/`system` args.
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 (atomic-chat-mcp-stdio.ts) makes runtime HTTP calls to the Atomic Chat host at http://host.docker.internal:1337 to send prompts (/v1/chat/completions) and return model completions to the agent, so that external model responses can directly affect agent behavior.
- 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.