Back to skill

Security audit

Competitor Intel

Security checks for vulnerabilities and agentic risk

Overview

This skill performs ordinary competitive research using public web sources and a simple local formatting script, with no hidden persistence or destructive behavior found.

Installers should treat this as a public-source competitive research helper. Avoid using it for private, deceptive, credentialed, or unauthorized monitoring, and review its outputs for source quality and currentness.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill references local repository resources such as scripts/build_matrix.py and files under references/, which implies file-read capability, but it does not declare any explicit tool scope or permissions boundary. That creates ambiguity about what filesystem access the agent may assume, increasing the risk of over-broad file access or unintended data exposure if the runtime grants more access than necessary.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language is very broad and includes phrases like 'competitive research,' 'market landscape,' and especially 'spy on competitors,' which can cause the skill to activate for a wide range of ambiguous requests. Overbroad activation increases the chance the skill is invoked in contexts involving unethical intelligence gathering, policy-sensitive surveillance requests, or irrelevant tasks where it may steer the agent toward unnecessary external collection and analysis.

Content

No source excerpt is available for this finding.