ClawHub
Back to skill

Security audit

雄韬CRM - opencrm

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward OpenCRM helper for reading and updating CRM records, with live-data risk that users should manage carefully.

Install this only for users who should access the live XTOCN CRM. Use a least-privilege OPENCRM_KEY, do not print or share the token, and require human review before creating or editing customers, tags, leads, contacts, or follow-up records.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables creation and modification of real CRM records, including customers, leads, contacts, and follow-up records, but does not require an explicit user-facing warning or confirmation for destructive or business-impacting writes beyond one narrow parse-to-add flow. This increases the risk of accidental real-world data changes, unauthorized updates, or integrity issues in production CRM systems when an agent executes actions too eagerly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Natural-language content across the file is presented exclusively in Chinese, which effectively forces a specific language for users and operators. The file does not mention that the skill is intentionally limited to Chinese-speaking users or offer any language/locale choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill instructs use of a bearer token via the OPENCRM_KEY environment variable but provides no handling guidance about keeping credentials secret, avoiding echoing them in logs, and not exposing them to users. While the document does not directly leak the token, omission of credential-safety guidance increases the chance of accidental disclosure during debugging or tool use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains all user-facing content in a single fixed language and does not mention any option to use another language or locale. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.