Security audit
shruwd
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Shruwd MCP connector for managing and reading brand visibility data, with no bundled executable payloads or hidden behavior found.
Install only if you intend to connect your agent to a Shruwd workspace. Use read-only OAuth scope for reporting-only workflows; grant read/write only when you want the agent to create or change brands, prompts, competitors, or measurements. Prefer the hosted OAuth setup unless you specifically need the local npm-based server.
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
Static analysis
No suspicious patterns detected.