Security audit

Swarm Layer

Security checks for vulnerabilities and agentic risk

Overview

The skill’s workflow automation is mostly disclosed and purpose-aligned, but its unpinned external plugin install paths and long-running automation controls should be reviewed carefully before use.

Before installing, pin the plugin to the reviewed 0.5.12 release or a specific audited commit and verify provenance where possible. Run it only in the intended project, start with dry-run/status commands, keep autopilot or watcher mode off until you understand the workflow, and review approvals instead of bulk-approving blindly.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:44
Finding: Unpinned External Plugin and Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill describes ACP automation, autopilot control, parallel dispatch, retry logic, and session follow-up capabilities without a clear upfront warning that automated execution may perform actions in the user's project. Because this is a workflow orchestrator designed to run tasks and steer sessions, insufficient disclosure increases the risk of users enabling automation that modifies files or project state beyond what they expected.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill describes ACP automation, autopilot control, parallel dispatch, retry logic, and session follow-up capabilities without a clear upfront warning that automated execution may perform actions in the user's project. Because this is a workflow orchestrator designed to run tasks and steer sessions, insufficient disclosure increases the risk of users enabling automation that modifies files or project state beyond what they expected.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.