Back to skill

Security audit

Sales Follow-Up Sequence

Security checks for vulnerabilities and agentic risk

Overview

The skill produces local draft plans and requires human-controlled outreach, although its script delivers less detail than advertised.

Manually complete and verify dates, channels and message text before outreach. Use a dedicated output folder because existing plan.md content is replaced. The optional Windows application linked through the [publisher's repository](https://github.com/rapidworker1/Multiple-AI-models-Toolkit) needs separate review; this verdict does not establish its safety.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The code is related to sales follow-up, but implements a generic weekly date list rather than the detailed deal-follow-up plan promised by the description. The missing touch, channel, and business-day logic constitutes a material functional mismatch. Local file reading and report writing are supporting implementation details; no unrelated execution, network access, or automatic outreach is present.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The generated plan lacks the promised per-touch channels and business-day gaps.

Low
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises a dated follow-up plan listing each touch, its channel, and its business-day gap. Instead, this loop emits dates at fixed calendar-day intervals with generic labels such as 'next block'; it neither assigns channels nor calculates or lists business-day gaps, and it can produce weekend dates.

Content

No source excerpt is available for this finding.