querit-search

SAFE max severity MEDIUMSkillSpector Do not install 99 registry clawhub.ai last scanned 2026-02-07 1 scan

Verdict safe, but 2 findings (2 medium), mainly data exfiltration. Most recent scan 2026-02-07.

The querit-search skill is a web search integration that poses MODERATE security risk. The primary concerns are supply chain security (unverified downloads from GitHub) and API key management practices. The skill does not exhibit malicious behavior such as data exfiltration, prompt injection, or command injection. However, the installation mechanism downloads code from an external repository without integrity verification, creating a supply chain vulnerability. The skill also requires an API key via environment variable without comprehensive security guidance. Missing optional metadata reduces transparency. The skill's core functionality (web search via external API) is legitimate and matches its description, but security hardening is recommended before production use.
Scanner's overall assessment (LLM analyzer)

Findings2

Critical0

High0

Medium2

Low0

Analyzersstatic llm meta

Second scanner: NVIDIA SkillSpector

VerdictDo not install 99

Score99 / 100

Issues14

CategoriesSupply Chain Tool Misuse Privilege Escalation

Version2.12.0 (static)

The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Web search via Querit.ai API. Use when you need to search the web for documentation, current events, facts, or any web content. Returns structured results with titles, URLs, and snippets.

Package: 8 files, 40 KB
SKILL.md: 313 words, 12+ sections
Code: JavaScript (2), Shell (1)
Requires: env: QUERIT_API_KEY

SKILL.md covers: Querit Search · Setup · Search · Extract Page Content · Output Format · Search results (default) · With --content · 1. Page Title · Extracted heading · With --json · When to Use · Limitations

Findings

MEDIUM Hardcoded External Repository Download Without Integrity Verification Data Exfiltrationllm

The install.sh script downloads files from a GitHub repository (https://raw.githubusercontent.com/interskh/querit-search/main) without any integrity verification (no checksums, signatures, or hash validation). This creates a supply chain risk where an attacker who compromises the GitHub repository or performs a man-in-the-middle attack could inject malicious code that would be executed on the user's system.

install.sh

REPO_BASE="https://raw.githubusercontent.com/interskh/querit-search/main"
FILES="SKILL.md search.js content.js package.json _meta.json"

for file in $FILES; do
  curl -fsSL "${REPO_BASE}/${file}" -o "${SKILL_DIR}/${file}"
done

Remediation: Implement integrity verification: (1) Include SHA-256 checksums for all downloaded files in the installer script, (2) Verify checksums after download before execution, (3) Use signed releases or Git commit hashes instead of 'main' branch, (4) Consider bundling dependencies within the skill package instead of downloading at install time.

MEDIUM API Key Exposure Risk via Environment Variable Data Exfiltrationllm

The skill requires QUERIT_API_KEY to be set as an environment variable and passes it to Node.js scripts. While environment variables are a standard practice, there is no documentation about secure handling, rotation policies, or warnings about API key exposure in logs or process listings. The skill metadata indicates this is the 'primaryEnv' variable, making it a critical credential.

SKILL.md:7

Needs env: `QUERIT_API_KEY` — get a free key at https://querit.ai (1,000 queries/month).

YAML metadata:
'primaryEnv': 'QUERIT_API_KEY'

Remediation: Add security guidance: (1) Document that API keys should never be committed to version control, (2) Recommend using secure credential storage (e.g., system keychain), (3) Warn users that environment variables may be visible in process listings, (4) Implement key rotation reminders, (5) Consider adding a check to warn if the key appears to be exposed in logs.

What is in the package

File	Kind	Size
`README.md`	doc	4.1 KB
`SKILL.md`	doc	2.7 KB
`_meta.json`	config	146 B
`content.js`	script	2.6 KB
`install.sh`	script	2.0 KB
`package-lock.json`	config	22 KB
`package.json`	config	303 B
`search.js`	script	6.3 KB

External hosts referenced

registry.npmjs.org github.com opencollective.com querit.ai raw.githubusercontent.com api.querit.ai

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

SKILL_DIR QUERIT_API_KEY

Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://clawhub.ai/skills/querit-search
Raw scan result: querit-search-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-querit-search.svg)
Request a re-scan