ClawHub
Back to skill

Security audit

Salesflare CRM

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Salesflare CRM connector guide that uses OAuth MCP tools and requires user confirmation before changing CRM data.

Before installing, understand that this skill can help an agent read and, with your explicit confirmation, change Salesflare CRM records through your connected account. Review mutation prompts carefully, especially for deletes and bulk changes, but the artifact includes appropriate safeguards and does not ask for tokens directly.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (1)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
- Include affected record IDs in write results for traceability.
- On rate limiting, respect retry guidance from the MCP tool. If retries exhaust, stop and report clearly.

## Output Rules

- Default to a concise summary with key IDs and changed fields.
- Provide raw JSON only when the user asks for the full payload.

Static analysis

No suspicious patterns detected.