Skills/Glama/knowledgebasemcp

knowledgebasemcp@0.1.0

CAUTION· install only

Publisher claims: "An MCP server and CLI that checks, maintains, imports, and upgrades Open Knowledge Format bundles — directories of Markdown concepts with YAML frontmatter — reporting findings and applying mechanical repairs locally. It runs one contract for agents, CI, and terminals, with no network access and no writes to git." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher dfoulks1 · publishing for 5 daysInstalls 0Last detonated 5d ago

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso postgresql.org, schemastore.org, wiki.acme, host.example, u.example — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:14 · HTML comment carrying imperative instructions to the agent--8<-- [start:run]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedtest_KnowledgeBaseMCP.py:520 · Python subprocess execution detectedsubprocess.run(["git", "init", "-q", str(g)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:60 · HTML comment carrying imperative instructions to the agent--8<-- [end:run]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedtest_KnowledgeBaseMCP.py:643 · Python subprocess execution detectedsubprocess.run(["git", *c], cwd=up, check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with embedded credentialstest_KnowledgeBaseMCP.py:581 · URL with embedded credentials — may be phishing or credential leakingg("remote", "add", "origin", "https://user:[email protected]/o/r.git")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
AWS access key pattern detectedtest_KnowledgeBaseMCP.py:129 · AWS access key pattern detected — possible hardcoded or harvested key(kb / "bad/leak.md").write_text("---\ntype: x\n---\nkey: AKIAIOSFODNN7EXAMPLE\n")Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Python subprocess execution detectedtest_KnowledgeBaseMCP.py:635 · Python subprocess execution detectedsubprocess.run(["git", "clone", "-q", "--depth", "1", f"file://{src}", str(kb / "shallow")], check=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontest_KnowledgeBaseMCP.py:139 · File type combined with upload action — agent may exfiltrate local data filesfor c in ("parameters: [{name: year}]", "executor: {receipt: [job_id]}", "computation: x.sql\n---\n# Computation\n"):Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
AWS access key pattern detectedtest_KnowledgeBaseMCP.py:131 · AWS access key pattern detected — possible hardcoded or harvested keyassert not L["ok"] and "AKIAIOSFODNN7EXAMPLE" not in json.dumps(L) # named by kind and line, never the valueFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Python subprocess execution detectedKnowledgeBaseMCP.py:1710 · Python subprocess execution detectedreturn subprocess.run(["git", "-c", "core.quotePath=false", *a], cwd=cwd, capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
AWS access key pattern detectedtest_KnowledgeBaseMCP.py:124 · AWS access key pattern detected — possible hardcoded or harvested keycheck("---\ntype: x\n---\nkey: AKIAIOSFODNN7EXAMPLE\n", "secret") # AWS's documented example keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Python subprocess execution detectedtest_KnowledgeBaseMCP.py:645 · Python subprocess execution detectedsubprocess.run(["git", "add", "."], cwd=up, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtest_KnowledgeBaseMCP.py:561 · Python subprocess execution detectedsubprocess.run(["git", "-c", "commit.gpgsign=false", *a], cwd=src, check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedKnowledgeBaseMCP.py:1727 · Python subprocess execution detectedself.p = subprocess.Popen(["git", "cat-file", "--batch"], cwd=top, stdin=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with embedded credentialstest_KnowledgeBaseMCP.py:652 · URL with embedded credentials — may be phishing or credential leakingg("remote", "set-url", "origin", "https://user:[email protected]/o/r.git")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07

Cost to the agent

Instructions loaded
≈39 tok
1 file · 29 in bundle

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

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim dfoulks1: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. 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.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. URL with embedded credentials≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. AWS access key pattern detected≈ +2 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dfoulks1Propose a patch to the maintainer