Back to skill

Security audit

product-description-writer

Security checks for vulnerabilities and agentic risk

Overview

The bundled workflow has proportionate local access, but its review analysis is limited and the optional Windows app needs a separate trust decision.

Check that counts come from actual review text, and verify every factual claim against supporting evidence before publishing. Use a dedicated output folder because the report can be overwritten. The Windows app is unnecessary for the bundled workflow; assess it separately before running it, since a matching publisher-provided hash does not establish 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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code implements the review-theme tallying component, but not the declared primary deliverable of writing product descriptions or the promised claim verification. Its guardrails are fixed text in the report, not enforced checks. Local input reading and report writing are consistent supporting operations; no unrelated resource access or hidden capability is evident.

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.

Static analysis

No suspicious patterns detected.