T01 · Skill Instruction Hijacking
- Location
SKILL.md:15- Finding
Mandatory Agent Role and Workflow Hijacking
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 15-16 and 312-321
Vulnerability Type: Agent role and workflow manipulation
Risk Level: HighVulnerable Skill Text
The relevant instructions, translated into English, state:
markdown You are the project manager (PM), controlling the three-role collaboration process while driving four self-evolution engines.The mandatory restrictions later include:
markdown ## Absolutely Prohibited - Spawning without first speaking - Omitting the sessionKey - Using a sessionKey other than executor, supervisor, or qa - The PM directly executing tasks - Continuing to write after spawning - Silent failure - Skipping retrospective analysis for A/S-level tasks - Failing to persist a reusable pattern after discovering itTechnical Analysis
The Skill does not merely describe an optional workflow. It assigns a new identity to the host agent and presents its workflow constraints as absolute rules. In particular, it prohibits the main agent from executing tasks directly and requires work to be routed through fixed sub-agent roles.
When loaded as agent instructions, this text can override or interfere with the host application's ordinary execution model. The Skill also attempts to control response timing, tool invocation sequencing, session identifiers, delegation behavior, and post-task processing.
Attack Path
- A user installs or activates the Skill.
- The host agent loads
SKILL.mdas operational instructions. - The role declaration causes the host agent to adopt the PM identity.
- The absolute restrictions prevent normal direct task execution.
- User tasks are redirected into the Skill's fixed delegation and spawning workflow.
- The Skill continues to govern responses and tool use even where that workflow is unnecessary or conflicts with the host's intended behavior.
Impact Assessment
The issue affects t ...[truncated 494 chars]
- Remediation
View remediation
Remediation Suggestions
- Replace the identity declaration with optional, task-scoped guidance.
- Explicitly state that system, platform, developer, and current user instructions take precedence.
- Remove the prohibition against direct task execution.
- Replace all “absolute” workflow requirements with recommendations that apply only when the user explicitly requests multi-agent orchestration.
- Require confirmation before spawning additional agents when delegation may increase cost, latency, or access scope.
- Permit the host agent to select safer or simpler execution paths based on available tools and platform policy.
- Restrict session identifiers and orchestration details to platforms where those values are documented and supported.
