Security audit
第三人称 NoFlatter · Anti-Sycophancy / 第三人称改写
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed prompt-reframing helper that asks the agent to answer from a neutral third-person perspective and shows no file, command, network, credential, or persistence behavior.
Install this if you want the assistant to reframe selected requests into a more neutral third-person brief before answering. The main effect is behavioral: responses may be more direct and less validating. There is no artifact evidence that it reads files, runs commands, uses credentials, contacts the network, or persists data.
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
Static analysis
No suspicious patterns detected.