T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:36- Finding
Persistent Storage of Reusable Account Credentials in Plaintext
- Content
View full analysis
- Remediation
View remediation
Security audit
Gurkerl
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent grocery-shopping skill, but it asks users to persist a reusable account password and enables real purchase and order changes without enough safety guidance.
Review this skill carefully before installing. Use it only for an account where agent-driven shopping actions are acceptable, protect the password storage with strict local permissions, avoid committing or sharing the service override, and require explicit review before checkout, payment, order cancellation, list deletion, or support-email actions.
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)
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 (2)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The setup instructions tell users to store account email and password in environment variables and persist them in a systemd service override, but provide no warning about credential exposure risks. Environment variables and service configuration files can be readable by local users, exposed through process inspection, logs, backups, or misconfigured permissions, making compromise of a real shopping account more likely.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The skill documents high-impact state-changing operations such as clearing carts, submitting checkout, cancelling orders, and deleting shopping lists without any cautionary guidance, confirmation expectations, or safe-use notes. In an agent-driven context, this increases the chance of accidental or unauthorized destructive actions being triggered from ambiguous prompts, especially because these actions affect real purchases and account state.
- Content
Static analysis
No suspicious patterns detected.