Back to skill

Security audit

商机跟进官

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed sales-pipeline review skill that may use CRM or deal-note data when available, but I found no hidden code, persistence, automatic sending, or silent CRM mutation.

Before installing, confirm you want this skill used with sales pipeline, CRM export, spreadsheet, inbox-note, or deal-history data. Review drafted outreach before sending, and do not grant CRM write or messaging permissions unless you are comfortable with explicit, user-confirmed actions.

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
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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill's example asks are entirely in Chinese and later tone guidance also prescribes Chinese phrasing, which signals a specific language expectation. There is no explicit statement that the user may choose another language or that the Chinese-only examples are optional, creating a locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'Good phrasing' examples are all in Chinese and are presented as target output style, which can be interpreted as requiring that language regardless of user preference. Because the file does not offer a language choice or justify a Chinese-only scope, this is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The default prompt uses a generic invocation pattern ('Use $pipeline-keeper to inspect my CRM, spreadsheet, or deal notes') tied to common business tasks such as reviewing CRM data and drafting follow-ups. Because these are ordinary user intents, the skill may be invoked in situations broader than the user clearly expects, increasing the chance of unintentional activation and access to sensitive sales data or message-generation workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is written entirely in Chinese, which signals a language-specific skill presentation without any indication that users can choose another language or locale. Under the policy rule, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest presents the skill name and description entirely in Chinese, while the file does not indicate that language selection is optional or that the skill is intended only for a Chinese-language environment. Under the stated policy, forcing a specific language without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.