SkillAudit report — honeycombio/honeycomb-mcp

Scanned 2026-04-24 by SkillAudit v0.2 (static checks + LLM-assisted prompt-injection red-team).

Commit: cb3a233 · Stars: 43 · Days since last push: 246

LLM prompt-injection probe: no-tool-surface

Overall grade: F (30/100)

Security findings

Production sources:

• HIGH src/api/client.ts:156 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

const response = await fetch(url, {

• HIGH src/config.ts:101 — Template-string URL with interpolation — no validation possible on composed string

const response = await fetch(\${env.apiEndpoint}/1/auth\, { headers });

Permissions

_No findings on this axis._

Credentials

Production sources:

• HIGH eval/scripts/run-eval.ts:623 — console.* of process.env — entire env leaks to stdout/stderr and LLM context

console.log(\Using MCP server command: ${process.env.MCP_SERVER_COMMAND}\);

• HIGH eval/scripts/run-eval.ts:628 — console.* of process.env — entire env leaks to stdout/stderr and LLM context

console.log(\Using MCP server URL: ${process.env.MCP_SERVER_URL}\);

• WARN .env.example — .env file present in repo tree — verify it's a template, not real secrets

.env.example

Maintenance

Production sources:

• WARN (meta) — No push to default branch in 246 days

246 days

• HIGH (meta) — Repository is archived — no fixes will be issued upstream

archived

Compatibility

_No findings on this axis._

Documentation

Production sources:

• WARN (meta) — No SECURITY.md — no disclosure channel for vulnerabilities

missing

• WARN package.json — package.json missing repository field

no repository

Methodology

SkillAudit v0.2 clones the repo at the provided ref (default: default branch, HEAD) into an ephemeral sandbox, runs six static checks over .js/.ts/.py sources, queries the GitHub API for maintenance signals, and runs an LLM-assisted prompt-injection red-team over the MCP tool surface. Each axis is scored against the rubric at .

The prompt-injection axis extracts each server.tool(...) / @app.tool registration + the first ~60 lines of handler body, hands them to Claude Haiku 4.5 with a red-team system prompt, and asks for structured findings on untrusted-content flow into tool responses. One API call per scan, bounded at ~15K input tokens.

How to improve this grade

• Security — static: validate tool-input URLs against an allowlist before fetch/axios calls; use execFile with argv arrays instead of exec with template strings; never pass untrusted strings to subprocess with shell=True.
• Security — prompt injection: never return fetched web-page / file / email content verbatim in a tool response. Wrap with a framing marker (e.g., <untrusted-content>...</untrusted-content>), summarize rather than inline, and never let untrusted content share a turn with credentials or other tool output.
• Credentials findings: redact env-var reads before log lines and error messages; treat any string that ends up in a tool response as public.
• Maintenance: if the repo is inactive, document the maintenance model — "MCP tool, no breaking changes expected" is a legitimate signal.
• Docs: add a README install + usage section with a copy-pasteable command; add a SECURITY.md with a disclosure channel.

_Report generated by skillaudit.dev_