Back to skill

Security audit

sales-meeting-notes

Security checks for vulnerabilities and agentic risk

Overview

The bundled workflow has limited local access, although its script only checks fields instead of creating the promised complete meeting notes.

Expect a field-check report, not finished meeting notes or verified dates. Use a dedicated output folder because reruns overwrite meeting-record.md. The optional Windows app is unnecessary for the bundled workflow and needs separate review; the supplied hash does not prove it is safe.

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
99% confidence
Finding

The primary output is a validation report, not the structured sales meeting record promised by the description. Input values are used only to calculate lengths and identify empty fields; their contents are omitted from the output. There is also no processing of raw notes or date validation. Local input reading and output writing are ordinary supporting operations, and no unrelated access or external communication 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 skill produces a field-validation report rather than the promised structured meeting record.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises to turn raw sales notes into decisions, commitments, open items, and a dated next step. At L93-L105, the code instead reads already-named fields and outputs only their character counts or validation status, discarding the actual meeting content; L117 writes that report as meeting-record.md. It neither structures raw notes nor extracts or validates a next-step date.

Content

No source excerpt is available for this finding.