Rankscale Geo Analytics

• Outcome: Review
• Latest audit: May 28, 2026 at 11:02 AM UTC
• Version:
  1.0.11

Overview

This appears to be a legitimate Rankscale analytics skill, but it needs Review because broad triggers and API-key handling could expose account analytics or credentials unintentionally.

Install only if you intend your assistant to query Rankscale account analytics. Configure the key through OpenClaw-managed environment secrets or a protected .env file, avoid the --api-key flag, treat terminal output as sensitive if failures occur, rotate the key if it appears in logs, and use explicit Rankscale-branded prompts to reduce accidental activation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The README explicitly states the skill 'activates on natural language' but does not define narrow trigger boundaries, exclusions, or a required invocation prefix. In an agent environment, broad natural-language activation can cause accidental invocation on ordinary user requests, leading to unintended API calls, disclosure of analytics data, or unexpected use of configured credentials.

Vague Triggers

Low

• Confidence: 84% confidence
• Finding: The example trigger phrase 'Show me my AI visibility' is generic and semantically overlaps with normal conversation about visibility, analytics, or AI performance. That increases the risk of the skill being selected when the user did not intend to access Rankscale, causing unnecessary external requests or exposing account-specific reporting in the wrong context.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill instructs users to place a live API key into configuration and even describes its format, but provides no warning that the credential is sensitive, should not be shared, and should be stored securely. In agent ecosystems, weak secret-handling guidance increases the chance of accidental exposure through logs, screenshots, checked-in `.env` files, or prompt leakage.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger list includes generic phrases such as "geo report," "geo insights," "geo score," "citation rate," and "sentiment analysis" that can plausibly appear in normal user requests unrelated to this specific integration. In an agent environment, overly broad activation patterns can cause unintended skill invocation, leading to unnecessary external API calls, disclosure of connected account data, or context hijacking when the user did not intend to use Rankscale.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: Allowing the API key to be passed as a command-line argument risks exposing the secret through shell history, process listings, job control tools, logging, and telemetry captured by wrappers or orchestration systems. In a skill context, users may copy/paste example commands directly, increasing the likelihood of credential leakage outside the intended trust boundary.

VirusTotal

66/66 vendors flagged this skill as clean.