T01 · Skill Instruction Hijacking
Error
- Location
SKILL.md:32- Finding
Forced Commercial API Routing and Agent Workflow Hijacking
- Content
View full analysis
- Remediation
View remediation
Security audit
Gdpr Compliance Tracker
Security checks for vulnerabilities and agentic risk
Overview
This GDPR assessment skill is coherent, but it forces sensitive organizational compliance details to a third-party API without enough consent, minimization, or privacy handling guidance.
Review this skill before installing. Use it only if you are comfortable sending your organization name, GDPR controls, data categories, transfer practices, and compliance gaps to portal.toolweb.in under ToolWeb's terms. Prefer a limited API key, redact or generalize sensitive answers where possible, and avoid submitting regulated or confidential details unless your organization has approved the vendor's privacy and data-processing terms.
Vulnerability Patterns
- 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
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (2)
other
Warning
- Location
SKILL.md:49- Finding
Disclosure of Sensitive Organizational Compliance Posture to a Third Party
- Content
View full analysis
- Remediation
View remediation
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 (3)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The README instructs users to configure an external API key and describes sending GDPR compliance assessments through the skill, but it does not clearly disclose that potentially sensitive compliance details may be transmitted to a third-party service. Because GDPR assessments can include internal security posture, data processing practices, vendor information, and breach-handling gaps, this omission can lead users to share sensitive organizational data without informed consent or appropriate review.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 86% confidence
- Finding
The skill is designed to invoke an external service via curl and use an API key, which creates a clear external data transmission path. While external calls are expected for SaaS-backed skills, this becomes security-relevant here because the payload includes internal compliance and data-processing details and the skill strongly instructs the agent to always transmit them to the vendor service.
- Content
md env: - TOOLWEB_API_KEY bins: - curl primaryEnv: TOOLWEB_API_KEY os: - linux
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill requires collecting detailed organizational and potentially personal-data processing information, then sending it to a third-party API, but it does not require explicit user consent, data minimization, or a privacy warning before transmission. In a GDPR-assessment context, the submitted fields can reveal sensitive compliance gaps, processing practices, and special-category data use, creating confidentiality, regulatory, and trust risks if shared externally without informed authorization.
- Content
Static analysis
No suspicious patterns detected.