Security audit

Multi Agent Protocol

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent protocol documentation, but its proposed task-store tools under-specify authentication for privileged phase, approval, and circuit actions.

Review before installing or implementing this skill in a shared or automated environment. It should be acceptable as protocol guidance only if the task-store plugin enforces server-side authenticated identities and capabilities, especially for task_transition, task_resolve_approval, and task_open_circuit; do not rely on caller-provided actor or role strings as authorization.

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: references/task-store-plugin.md:188
Finding: Caller-Controlled Identity Fields Permit Authorization Spoofing in Privileged Task-Store Tools
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

Findings (1)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.
md
1. `SKILL.md`

Static analysis

No suspicious patterns detected.