Back to skill

Security audit

vendor-comparison-sheet

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence, mainly because a scanner confirmed that its vendor-ranking script can turn missing or malformed vendor terms into numeric scores that may skew rankings.

Review the skill’s permissions and the confirmed scoring behavior before installing. If you use its rankings, check missing or malformed vendor terms yourself; the scan was partial because several referenced paths could not be resolved.

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.

Missing vendor terms are reported as zero despite the documented requirement to leave them unknown.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The scoring loop converts missing values to 0.0 and nonnumeric values to 1.0, then presents these invented values as numeric facts in the ranking. In a procurement decision tool, this undermines report integrity and lets incomplete or malformed vendor data alter rankings without a clear warning, contrary to the explicit requirement to preserve unknown terms.

Content

No source excerpt is available for this finding.