Security audit

curate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed documentation helper that saves user-provided annotations into a project-local knowledge base file.

Install this if you want Codex to help capture project rationale for gauntlet. Be aware that saved annotations may influence future gauntlet challenges, so only record information you actually want reused in that project context.

A.I.G

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

SkillSpector

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest trigger 'capturing tribal knowledge or rationale not visible in code' describes a broad situation rather than a specific invocation phrase or constrained activation condition. Without explicit trigger phrases, scope limits, or negative examples, the skill could be invoked in many ordinary development conversations about documentation or rationale.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.