trove@0.1.0
CAUTION· install onlyPublisher claims: "Shared memory for your AI agents. Claude Code, Codex, Cursor and any other MCP client read and write one knowledge graph: every fact shows its source, and stale facts get replaced. Open source and self-hostable, with a hosted version at https://mytrove.in" Observed in sandbox: reads credential files.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
Code inventory arrives with this version's next honeypot run.- It will ask for
- unknown until the next run
- Where it talks to
- unknown until the next run
- What the honeypot saw
- read ~/.npmrc · reached only registry.npmjs.org
- What we could not test
- use of the skill by an agent
Connect it only under the guard, with no real credential files on the machine it runs on. It read ~/.npmrc, which is nothing an MCP server needs from a user. `--contain` makes those directories unreadable.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-07 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Prompting user to enter sensitive credentials; Access to sensitive file paths. Summary: reads credential files.
Behavior trace
Honeypot run · 2 s · 2 scenariosStatic findings
// .env is optional; real environment variables always win.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Enter your API key to open the dashboard.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// Profile fetch failing shouldn't kill auth; proceed with what the JWT proves.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.process.loadEnvFile(new URL("../.env", import.meta.url).pathname);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// --- Env: load .env for OPENAI_API_KEY / TROVE_EMBEDDING_PROVIDER, then FORCE theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// Profile fetch failing shouldn't kill auth; proceed with what the token proves.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.process.loadEnvFile(new URL("../.env", import.meta.url).pathname);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.process.loadEnvFile(new URL("../.env", import.meta.url).pathname);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Hosted MCP: `https://mytrove.in/mcp` with a `trove_*` API key or service token. Local dev: `cd ~/dev/trove && docker compose up -d postgres && npm start`; tokens in `.env` (`TROVE_SERVICE_TOKENS`); heFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// .env optional; real environment wins (process.loadEnvFile does not override).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.process.loadEnvFile(new URL("../.env", import.meta.url).pathname);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."lint": "npx oxlint src scripts tests",Fix: Pin versions and sources; vendor anything fetched at install time.// .env is optional; real environment variables always win.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// .env is optional; real environment variables always win.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.`When a node exhausts available memory, the kubelet terminates container workloads to reclaim capacity, and the scheduler rebinds the interrupted workloads onto healthier machines. Covers OOM-kill behFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.* the provider and name the model in `TROVE_CHAT_MODEL` (see .env.example).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// scratch DATABASE_URL (never trust whatever .env points at) and assert it.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* `npx skills add` install, the `/skills.md` and `/skills/<name>.md` routes,Fix: Pin versions and sources; vendor anything fetched at install time."npx skills add anunay999/trove -g",Fix: Pin versions and sources; vendor anything fetched at install time.const SKILLS_INSTALL = "npx skills add anunay999/trove -g";Fix: Pin versions and sources; vendor anything fetched at install time.const input = await parseJsonOrThrow(context.req.json(), readInputSchema);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.* gothic theme — built by `npx astryx theme build`Fix: Pin versions and sources; vendor anything fetched at install time.const SKILLS_INSTALL = "npx skills add anunay999/trove -g";Fix: Pin versions and sources; vendor anything fetched at install time.const input = await parseJsonOrThrow(context.req.json(), searchInputSchema);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.return context.json(await store.search(input, operationContextFromAuth(auth)));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.// pasting. Same files as the npx install and the MCP prompts (src/skills.ts).Fix: Pin versions and sources; vendor anything fetched at install time.* Serving posture for one McpServer instance. The HTTP handler constructs oneFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.return context.json(await store.neighborhood(input, operationContextFromAuth(auth)));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const input = await parseJsonOrThrow(context.req.json(), neighborhoodInputSchema);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.* To refresh one: npx -y simple-icons@latest, then read `.path` off the export.Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/.npmrc.
- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim anunay999: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.