brain-core-mcp@0.16.1
CAUTION· not startedPublisher claims: "A memory for your Claude Code agent that survives the session: one local MCP server, five tools, a markdown vault, an eval." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso githubusercontent.com, astral.sh — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.13.0
vet-skills diff brain-core-mcp 0.13.0 0.16.1In the sandbox, this version reached for nothing 0.13.0 did not. Compared from the two recorded runs, not from source.
0.13.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-22 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collects environment variables by secret-like names; URL with embedded credentials; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
env = {k: v for k, v in os.environ.items() if k != "ANTHROPIC_API_KEY"}Fix: Never read or enumerate credential locations; accept a documented environment variable instead.# user:password@ in a URL; a comma is not in one ("http://localhost:8080,[email protected]")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.cp = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cp = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cp = subprocess.run(["crontab", "-l"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["crontab", "-"], input=merged, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.raise RuntimeError("uv is required: curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.md = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.model. A raw row keeps names as written; brain.db resolves them to entities when it computesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.subprocess.run(["crontab", "-"], input=after, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.raise RuntimeError("uv is required: curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.except Exception as e: # a broken graph net must not kill recallFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.js = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Write a whole agent: brain.yaml, CLAUDE.md, rules, skills, hooks, .mcp.json, vault."""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.except Exception as e: # a dead store must not kill recallFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# an exact version: `npx -y` with a bare name runs whatever npm resolves that dayFix: Pin versions and sources; vendor anything fetched at install time."""The claims tier in brain.db (M3, audit G.2): raw rows per source, and the claims computedFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.row = self.db.fetchone("SELECT dirty, inputs FROM claims_state WHERE id = 1")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.info = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.Popen( # outlives this command; the Run key starts it again at the next logonFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cp = subprocess.run(["crontab", "-l"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["launchctl", "bootout", f"gui/{os.getuid()}", str(p)], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cp = subprocess.run(["crontab", "-l"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["systemctl", "--user", "daemon-reload"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim xy-claude: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Collects environment variables by secret-like names≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.