Security audit
Howto Docs
Security checks for vulnerabilities and agentic risk
Overview
This skill is a documentation-writing guide and does not ask the agent to run code, access private data, or persist changes.
This appears safe to install as writing guidance for how-to documentation. Its examples mention API keys, webhook secrets, and install commands only as sample documentation content, not as instructions for the agent to collect secrets or execute commands. Make sure the referenced docs-style companion skill is available if you want the dependency links to resolve.
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