code-mode
Add a "code mode" tool to an existing MCP server so LLMs can write small processing scripts that run against large API responses in a sandboxed runtime — only the script's compact output enters the LLM context window. Use this skill whenever someone wants to add code mode, context reduction, script execution, sandbox execution, or LLM-generated-code processing to an MCP server. Also trigger when users mention reducing token usage, shrinking API responses, running user-provided code safely, or adding a code execution tool to their MCP server — in any language (TypeScript, Python, Go, Rust, etc.).
89
85%
Does it follow best practices?
Impact
95%
2.20xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. 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's required workflow explicitly states the MCP tool "executes the underlying API call" and passes the raw API response into the sandbox as a DATA variable (SKILL.md Step 3a / Step 4 and references/benchmark-pattern.md which even suggests "Hit real API"), meaning the agent will ingest untrusted, user-generated/public third‑party responses (e.g., GitHub, Slack, SCIM, Kubernetes) and use the processed output to drive subsequent reasoning/actions.
- Repository
- chenhunghan/code-mode-skill
- Path
SKILL.md
- Commit
3a2240a
- 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.