Back to skill

Security audit

Pilot Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned, but its approval workflow can incorrectly treat unverified or duplicate messages as independent approvals.

Review this carefully before installing. It is not obviously malicious, but do not rely on it as a security-grade approval gate unless you add authenticated reviewer identity checks, deduplication, strict task/request binding, deadlines, safe JSON construction, and fail-closed error handling.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:89
Finding

Approval Threshold Can Be Bypassed with Unauthorized or Duplicate Reviews

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:44
Finding

Untrusted Values Are Interpolated Directly into JSON and jq Programs

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep