Security audit
Why did my request fail? Should I retry?
Security checks for vulnerabilities and agentic risk
Overview
This skill gives retry guidance for failed network requests using a disclosed local diagnostic plugin and does not include executable code or hidden behavior.
Install this if you want agents to make fewer blind retries after network failures. Be aware that useful operation depends on the clawphylax plugin and its local ledger of observed request outcomes, so review that plugin's data collection behavior separately.
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