Security audit
Skill Sprint Pack Builder
Security checks for vulnerabilities and agentic risk
Overview
This skill is a text-only helper for turning user-provided notes into a public-safe lesson and skill pack, with clear privacy and redaction guardrails.
Before installing, users should understand that the skill is designed for public-safe rewriting, not for copying paid lessons, private community content, customer records, credentials, or screenshots. Its requested behavior is proportionate, but users should still review outputs for private names, links, account details, claims, and other sensitive data before posting publicly.
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
