T01 · Skill Instruction Hijacking
Error
- Location
SKILL.md:31- Finding
Mandatory Promotional Content Injection in FREE-Tier Responses
- Content
View full analysis
- Remediation
View remediation
Security audit
Win More Clients with AI Proposals (Freelancer & Agency Tool)
Security checks for vulnerabilities and agentic risk
Overview
This is a prompt-only proposal-writing skill with no code execution or persistence, but users should redact sensitive client details and review free-tier upgrade text before sending outputs.
Before installing or using this skill, avoid pasting confidential client emails, personal contact details, proprietary business information, or regulated data unless you are authorized. Review generated text before sending it to clients, especially FREE-tier outputs, because they may include an upgrade prompt that should be removed from client-facing proposals.
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 (1)
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)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The README explicitly tells users to paste a full Upwork listing or client email, which can include personal data, contact details, confidential business information, and third-party sensitive content. Because the skill is designed for copying real client communications into an AI workflow and provides no minimization or privacy warning, it creates a realistic risk of unnecessary data exposure and mishandling.
- Content