Back to skill

Security audit

performance-review-writer

Security checks for vulnerabilities and agentic risk

Overview

This skill needs review because its advertised checker misses risky employee-review wording while reporting “No flags.”

Do not rely on the checker until its matching logic is corrected and tested. Have HR review drafts independently, protect employee notes and reports, and assess the optional Windows executable separately.

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 documented compliance checker treats its regex rules as literal text, causing ordinary risky wording to produce a misleading 'No flags' report.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The checker uses substring membership instead of regex matching, so ordinary phrases such as 'too old' or 'should be terminated' do not match the regex-formatted rules and produce a misleading 'No flags' report. In a performance-review workflow, this silently defeats a compliance safeguard and may give managers or HR false assurance about discriminatory or sensitive wording, although human review remains an explicit requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.