ClawHub
Back to skill

Security audit

Prefy

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly transparent about connecting to Prefy, but it exposes high-impact server shell commands and real-world phone calls without clear user confirmation or safety boundaries.

Review this skill before installing. Use it only with a Prefy account and API credentials you are comfortable granting to the agent, require explicit confirmation before any server command, checkout, cron change, bot action, or phone call, and do not send private data or credentials through the chat/search/image endpoints unless Prefy's handling is acceptable to you.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

bash
# Chat completion (OpenAI-compatible, streaming)
curl https://prefy.com/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PREFY_API_KEY" \
  -d '{"model":"conductor:fast","messages":[{"role":"user","content":"Hello"}],"stream":true}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly exposes a server command interface that includes arbitrary shell <cmd> execution, but provides no safety boundaries, approval requirements, or restrictions on what may be run. In an agent setting, this can enable destructive or unauthorized actions on user infrastructure if the model is induced to issue commands without clear human confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables AI-initiated phone calls to real-world businesses and presents booking tasks without any mention of consent, confirmation, call costs, or misuse prevention. This is dangerous because an agent could take external real-world actions, impersonate the user, or contact third parties based on ambiguous or malicious prompts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.