Security audit

ai-prompt-engineering-safety-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only prompt review template that focuses on safer prompt design and does not request tools, credentials, persistence, or system access.

Install this if you want structured safety and quality feedback on prompts. Use judgment when asking it to rewrite prompts: it should be used to make prompts safer and clearer, not to optimize harmful or policy-evading requests.

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

Confidence: 91% confidence
Finding: The skill is scoped so broadly that it can be invoked for many generic prompt-review or prompt-improvement requests, which increases the chance it will override a more specific, safer, or policy-constrained skill. Because it also instructs the agent to generate improved prompts, an attacker could use this broad activation surface to launder unsafe intent through a 'safety review' workflow and obtain optimized harmful prompts.

Static analysis

No suspicious patterns detected.