Security audit
Prompt Fidelity
Security checks for vulnerabilities and agentic risk
Overview
This skill is a transparent prompt-quality checklist that helps separate verified facts from judgment, with no evidence of hidden access, persistence, or data exfiltration.
This appears safe to install from a security perspective. Be aware that the skill tells the agent to run a helper script that is not included in this artifact, so it may not work as written unless that script is supplied separately; also review any database or API queries it proposes before running them on large or sensitive systems.
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
- 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