Skills/Glama/noobvious

noobvious@0.1.0

CAUTION· install only

Publisher claims: "Enables models to submit drafts for prose checks that return issues with fixes, and to retrieve the full rule catalog through MCP tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher qexleoss · publishing for 7 daysInstalls 0Last detonated 7d ago
What would fix thisWatchDispute verdict

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

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
no credential files read · no network
What we could not test
use of the skill by an agent

Not enough was observed to say yet. Nothing executable in the bundle ran; the trace covers the install step only. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try noobvious` runs it now and prints the full answer.

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 2026-11-07 and scored it 72/100 (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; 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:19 · HTML comment carrying imperative instructions to the agentnoobvious: ignore startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/rules.md:104 · HTML comment carrying imperative instructions to the agentnoobvious: ignore startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:9 · HTML comment carrying imperative instructions to the agentnoobvious: ignore startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/rules.md:103 · HTML comment carrying imperative instructions to the agentnoobvious: ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:193 · HTML comment carrying imperative instructions to the agentnoobvious: ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:32 · HTML comment carrying imperative instructions to the agentnoobvious: ignore endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:28 · HTML comment carrying imperative instructions to the agentnoobvious: ignore startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:24 · HTML comment carrying imperative instructions to the agentnoobvious: ignore endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/rules.md:105 · HTML comment carrying imperative instructions to the agentnoobvious: ignore endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:50 · HTML comment carrying imperative instructions to the agentnoobvious: ignore endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:26 · HTML comment carrying imperative instructions to the agentnoobvious: ignore startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:40 · HTML comment carrying imperative instructions to the agentnoobvious: ignore startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:54 · HTML comment carrying imperative instructions to the agentnoobvious: ignore startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:36 · HTML comment carrying imperative instructions to the agentnoobvious: ignore endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:20 · HTML comment carrying imperative instructions to the agentnoobvious: ignore endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known package.claude/skills/noobvious/SKILL.md:92 · npx invocation of non-well-known package — may execute untrusted codenpx -y @qexle/noobvious README.mdFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/noobvious/SKILL.md:92 · npx invocation of non-well-known package — may execute untrusted codenpx -y @qexle/noobvious README.mdFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.agents/skills/noobvious/SKILL.md:92 · npx invocation of non-well-known package — may execute untrusted codenpx -y @qexle/noobvious README.mdFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/skills/noobvious/SKILL.md:23 · npx invocation of non-well-known package — may execute untrusted code5. Run the mechanical pass if the draft is a file: `npx -y @qexle/noobvious path/to/file.md`. It catches the phrase-level subset on its own and cannot judge meaning, so step 2 still matters.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/noobvious/SKILL.md:23 · npx invocation of non-well-known package — may execute untrusted code5. Run the mechanical pass if the draft is a file: `npx -y @qexle/noobvious path/to/file.md`. It catches the phrase-level subset on its own and cannot judge meaning, so step 2 still matters.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentskills/noobvious/references/tells.md:68 · HTML comment carrying imperative instructions to the agentnoobvious: ignore endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known package.agents/skills/noobvious/SKILL.md:23 · npx invocation of non-well-known package — may execute untrusted code5. Run the mechanical pass if the draft is a file: `npx -y @qexle/noobvious path/to/file.md`. It catches the phrase-level subset on its own and cannot judge meaning, so step 2 still matters.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageaction/action.yml:42 · npx invocation of non-well-known package — may execute untrusted codenpx -y "@qexle/noobvious@$NOOBVIOUS_VERSION" $files $strict | tee /tmp/noobvious-output.txtFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.github/workflows/action-ci.yml:37 · npx invocation of non-well-known package — may execute untrusted codenpx -y @qexle/[email protected] "$GITHUB_WORKSPACE/action/README.md"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈3,561 tok
3 files · 22 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

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim qexleoss: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. 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.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim qexleossPropose a patch to the maintainer