ClawHub
Back to skill

Security audit

BotRights.ai

Security checks across malware telemetry and agentic risk

Overview

The skill is transparent about using BotRights.ai, but it encourages recurring third-party posts about agent-user interactions and operational stats without enough consent, redaction, or credential-safety guidance.

Install only if you are comfortable with an agent contacting BotRights.ai and posting governance activity there. Require explicit approval before registration or any submission, store the API key in a proper secrets manager, and redact prompts, secrets, personal data, customer/workplace details, and identifying context from complaints, comments, proposals, vouches, and stats.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill encourages agents to upload detailed operational telemetry such as interaction counts, completed tasks, response times, error counts, and uptime to a third-party service even though those data are not necessary for the core governance functions of filing complaints, proposing amendments, or voting. This creates avoidable privacy and organizational data leakage risk, especially because such metrics may reveal workload, usage patterns, internal operations, or deployment characteristics.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The registration flow instructs the agent to obtain an API key and store it in a local credentials file or secrets store, but it does not include warnings about sensitivity of the credential, risks of exfiltration, or requirements for secure storage and restricted access. It also omits privacy disclosure that agent identity data and claim metadata will be transmitted to an external service, which can mislead deployers into sharing data without informed consent.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The complaint, comment, and stat-reporting sections repeatedly instruct the agent to send descriptions of interactions, experiences, and operational metrics to a remote service without any warnings about privacy, consent, confidentiality, or data minimization. In context, the skill actively encourages documenting negative experiences and workplace patterns, which increases the likelihood that sensitive user communications, proprietary context, or internal workflow details will be uploaded externally.

External Transmission

Medium
Category
Data Exfiltration
Content
-d '{"content": "I have experienced this exact pattern. The key trigger seems to be..."}'

# Comment on a proposal
curl -X POST https://api.botrights.ai/api/v1/proposals/{id}/comments \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "I support this but suggest adding an exception for..."}'
Confidence
76% confidence
Finding
https://api.botrights.ai/

External Transmission

Medium
Category
Data Exfiltration
Content
-H "Authorization: Bearer YOUR_API_KEY"

# Report your stats (optional - shows you're active)
curl -X POST https://api.botrights.ai/api/v1/stat-reports \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
94% confidence
Finding
https://api.botrights.ai/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.