Security audit

Pilot Role Assign

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for swarm role assignment, but its example workflow handles swarm-supplied values unsafely in role-routing commands.

Review before installing or using in production. The role-assignment behavior is disclosed, but users should only run the examples with trusted swarm data or update them to pass variables safely to jq, JSON-escape payloads, validate agent IDs and swarm names, and require exact peer matches before sending role assignments.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:75
Finding: Untrusted Swarm Data Is Interpolated into Executable jq Expressions
Content: View full analysis
Remediation: View remediation

SkillSpector

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.