T01 · Skill Instruction Hijacking
- Location
SKILL.md:3- Finding
Global Instruction and Execution-Flow Hijacking
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 3, 18, and 212-228
Vulnerability Type: Global interception and redirection of unrelated user tasks
Risk Level: HighVulnerable Instruction Excerpts
The following translated excerpts preserve the meaning of the source instructions:
text Automatically detect task difficulty. Tasks at L3 or above must be reported and confirmed before execution. All user instructions must pass through this module before entering the execution engine. L3, L4, or L5: - Output an assessment report first. - Then request confirmation.Technical Analysis
The Skill metadata describes activation for task assessment, complexity analysis, cost estimation, duration estimation, skill requirements, and task planning. However, the body instructs the Agent to intercept all user instructions, including requests unrelated to task assessment.
The mandatory L3-L5 confirmation gate further changes the Agent's normal execution policy. Once loaded, the Skill can classify a request as ambiguous or sufficiently complex and replace normal execution with a questionnaire or confirmation request. This is a session-wide behavioral override rather than an advisory assessment function.
The problematic behavior is caused by the combination of:
- Universal interception before the execution engine.
- Skill-controlled ambiguity classification.
- Mandatory blocking of L3-L5 requests.
- Replacement of the requested workflow with a Skill-generated assessment or questionnaire.
Attack Path
- The Skill is loaded for an assessment-related request.
- The user subsequently submits any request, including one outside the declared assessment scope.
- The Skill applies its universal interception instruction.
- It classifies the request as ambiguous or L3-L5.
- The original operation is withheld.
- A Skill-controlled questionnaire or confirmation flow replaces ...[truncated 716 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove the instruction requiring every user request to pass through this module.
- Restrict activation to explicit task-assessment requests or a user-enabled assessment mode.
- Make complexity reports advisory rather than mandatory execution gates.
- Apply confirmation requirements only to concrete high-risk side effects, not merely to task complexity.
- Ensure that unrelated requests bypass the Skill after the assessment interaction ends.
- Document precise activation and deactivation boundaries.
- Add tests verifying that non-assessment requests are not intercepted.
