patent-search

Security checks across static analysis, malware telemetry, and agentic risk

Overview

Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.

This appears suitable if you intend to use 9235.net for patent search. Before installing, obtain and protect a dedicated API token, understand that your patent queries go to the external provider, and be cautious with sensitive business or invention details. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI03: Identity and Privilege Abuse
Low
What this means

You must provide a 9235.net API token, and the skill will use it to authenticate patent API requests.

Why it was flagged

The skill requires a third-party API credential, even though the registry metadata lists no required env vars or primary credential. The credential use is disclosed and purpose-aligned, so this is a notice rather than a concern.

Skill content
credentials_required: true
credential_env_vars:
  - PATENT_API_TOKEN
openclaw_skill_api_key: "skills.entries.patent-search.apiKey"
Recommendation

Use a dedicated token if possible, keep it out of logs/screenshots, and rotate it if exposed.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

Patent searches, company names, and analysis queries may be visible to the external patent API provider.

Why it was flagged

The skill sends user search terms and patent identifiers to a disclosed third-party API, which is expected for this integration but still affects privacy for sensitive research queries.

Skill content
Endpoint: `https://www.9235.net/api` (HTTPS).
Data sent: Search queries, patent identifiers, pagination/filters, etc.
Recommendation

Avoid submitting confidential strategy or unreleased invention details unless you are comfortable with the provider’s terms and privacy policy.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

Manual setup or tests may fail or require users to infer missing Python dependencies.

Why it was flagged

The README references a requirements.txt file, but the provided manifest does not include one. There is no automatic install step shown, so this is a packaging/completeness note rather than evidence of unsafe execution.

Skill content
pip install -r requirements.txt
Recommendation

Confirm dependencies from a trusted source before manually installing anything, and prefer a complete package with pinned requirements.

#
ASI09: Human-Agent Trust Exploitation
Low
What this means

Users could overestimate the privacy protections for sensitive patent or business-intelligence searches.

Why it was flagged

The README makes broad privacy/security claims. Other documentation more concretely says queries are sent to a third-party provider, so users should not treat these marketing claims as a guarantee.

Skill content
- End-to-end encryption for API calls
- No storage of sensitive search queries
- GDPR compliant
Recommendation

Review the provider’s privacy policy and avoid relying solely on broad compliance or encryption statements.