Back to skill

Security audit

US Business SOP Builder

Security checks for vulnerabilities and agentic risk

Overview

The scanners flag a mismatch between the skill’s stated SOP-building purpose and the reported behavior of its script, so ClawScan classifies it as suspicious for review; no malicious intent is established.

Consider the skill’s stated purpose versus its reported linting behavior, and check what file access its host runtime allows before installing. The scan is partial because several local path references were unresolved, so the report does not provide complete evidence.

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
99% confidence
Finding

The supplied script only reports issues in existing text. Its section checks are case-insensitive substring searches, not validation or construction of a structured SOP. Although linting could support a broader SOP-building workflow, this code chunk does not implement the declared transformation and has a materially different primary function. Its local input-file reading and report writing are consistent with that linting function; no unrelated resource access or malicious behavior 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.