Security audit
Resolve Beagle
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed spec-review workflow that reads project context, researches open questions, edits the target spec, and only commits after user approval.
Before installing, be aware that this skill can read project files relevant to a spec, use external web research when a question needs it, and rewrite the spec in place. Its workflow requires user confirmation before research proceeds and before any commit, so it is appropriate for users who want an agent to help finalize planning documents while retaining review control.
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