ClawHub
Back to skill

Security audit

Competitor Research Playbook

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only competitor research playbook with no executable behavior, though users should apply care around broad triggers and outreach advice.

Installers should treat this as a strategic research checklist, not permission to scrape, spam, impersonate, or contact people at scale. Use public sources, respect platform rules, and keep outreach transparent and opt-in where possible.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list contains broad, generic phrases such as "market research" and "growth flywheel" that are likely to match many unrelated user requests. In an agent environment, this can cause the skill to activate outside its intended scope and steer benign queries into competitor-intelligence workflows, increasing the chance of unnecessary data collection or ethically questionable guidance.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The when_to_use section repeats generic trigger phrases without boundaries, exclusions, or disambiguation rules. This makes overbroad activation more likely and can route ordinary research or strategy requests into a playbook that encourages competitor surveillance and aggressive growth analysis methods not appropriate for all contexts.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This section recommends contacting or targeting a competitor's followers as a seed-user pool without any privacy, consent, platform-policy, or harassment safeguards. In context, the skill is a competitive-intelligence playbook, so guidance like direct messaging competitor audiences can readily be operationalized into invasive outreach, spam, or borderline social engineering behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.