Back to skill

Security audit

Ten Defeats

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad but transparent workflow guardrail for software tasks, with no code execution, data access, or hidden behavior found.

Install this if you want Codex to apply stricter planning, evidence, and verification discipline across non-trivial software tasks. Be aware it is intentionally broad and may shape many coding sessions automatically.

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
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says to use this skill for nearly any non-trivial software task, including planning, design, implementation, debugging, testing, review, verification, tool coordination, and delegation. This trigger scope is extremely broad and lacks concrete boundaries or negative examples beyond a few exclusions, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables implicit invocation with no visible trigger constraints, which can cause the agent to activate this skill in situations beyond the intended scope. Because this skill influences judgment, evidence, and completion claims for non-trivial software work, over-broad automatic activation can alter agent behavior unexpectedly and expand the blast radius of any bad instructions or prompt defects tied to the skill.

Content

No source excerpt is available for this finding.