Security audit
AgentCrawl
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently helps agents read web pages through a local AgentCrawl CLI/MCP server, with disclosed setup, network use, and safety limits.
Install only if you want a local web-scraping helper available to your agent. Prefer pipx isolation, review the AgentCrawl package source/publisher if supply-chain provenance matters to you, keep crawl limits small, and only enable private-network or local-file access when you intentionally need it.
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.