Back to skill

Security audit

Competitive Analysis Report

Security checks for vulnerabilities and agentic risk

Overview

The skill performs a limited local reporting task, but its reports need manual checks because source validation and template handling are incomplete.

Check every figure and source manually. The supplied YAML template currently produces empty report sections because the script expects heading-based notes. Choose an output folder where replacing digest.md is acceptable. Evaluate the optional unsigned Windows app separately; this verdict covers the inspected skill bundle.

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)

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 report builder does not provide the promised source log for every figure.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The manifest promises a source log for every figure, but this loop copies note content into sections without checking or associating figures with sources. Notes containing unsourced revenue, pricing, or customer counts are therefore included unchanged, even when the Source log section is populated only with a 'no notes' placeholder.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.