Back to skill

Security audit

Sales Pipeline Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local sales pipeline helper that stores and edits deal records in a disclosed JSON file, with no evidence of hidden network access or malicious behavior.

Install only if you are comfortable keeping sales pipeline records, contact names, emails, deal values, and notes in a local JSON file. Back up ~/.openclaw/workspace/sales-pipeline-agent/pipeline.json before relying on it, and be careful with delete actions because the bundled CLI removes records without a confirmation step.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill advertises local JSON persistence and exposes operations that add, update, and delete deals, but it does not declare any explicit tool scope or permissions boundary. That mismatch can cause users or the platform to underestimate the skill's ability to write and remove local data, increasing the chance of unintended file modification or destructive actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The example trigger phrase "Give me a pipeline summary" is broad, natural language that could plausibly appear in unrelated conversation and accidentally invoke the skill. Because this skill can read and modify locally stored deal data, unintended activation could expose sensitive sales information or lead to accidental state changes if follow-on actions are taken.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description notes local storage but does not explicitly warn that the skill permanently stores business deal data and supports permanent deletion. In a sales context, this can affect sensitive commercial records, and users may unknowingly expose or destroy pipeline information without understanding retention and deletion consequences.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The delete command triggers delete_deal and permanently removes a deal from the local pipeline database, but there is no confirmation prompt, warning message, or other user disclosure before the destructive action occurs. Because this operation deletes user-managed sales data, the lack of any explicit warning makes accidental or unintended data loss more likely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.