Back to skill

Security audit

create-technology-competitive-intelligence-rd

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps generate reviewed competitive-intelligence HTML reports and does not show hidden, destructive, or deceptive behavior.

Before installing, make sure users are comfortable providing reviewed competitive-intelligence data and using any optional PatSnap or public-source connectors needed for evidence gathering. Choose the output path deliberately because the renderer will create parent directories and write the requested HTML file.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code does not substantiate the rich declared functionality. It merely forwards execution to another module's main() function, with a docstring indicating a localized report renderer. Since the actual visible behavior is only a generic CLI wrapper and not evidence of the declared competitive-intelligence/reporting features, the description materially overstates what this code chunk itself does. While additional functionality may exist in generate_report, it is not present in the provided chunk, so the description is not accurately represented by the supplied code.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill instructs the agent to read templates and generate output files via a script, which implies file read/write capability, but it does not declare any explicit tool scope or permissions boundary. In an agent environment, undeclared file access increases the risk of over-broad filesystem interaction, unintended access to sensitive local data, or writing artifacts to unsafe locations if the runtime grants default capabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The HTML root element sets lang="en", which hard-codes English as the document language. Under the policy rules, forcing a specific language without user opt-in or a documented justification is a natural-language locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

Line L0002 sets the HTML document language to "en", which imposes an English locale by default. The file does not indicate user opt-in for language selection or explain that the template is intentionally restricted to an English-only, region-specific workflow.

Content

No source excerpt is available for this finding.