T09 · Insecure Skill Coding Practices
Error
- Location
scripts/run_mindmap_task.mjs:126- Finding
Unrestricted API Endpoint Override Can Exfiltrate Credentials and User Content
- Content
View full analysis
- Remediation
View remediation
Security audit
Felo Mindmap
Security checks for vulnerabilities and agentic risk
Overview
The skill mostly does what it claims, but it includes an undocumented endpoint override that can redirect the user's API key and mindmap prompt to an arbitrary server.
Review this skill before installing. Use it only in an environment where FELO_API_BASE is unset or tightly controlled, and avoid sending secrets, regulated data, or confidential notes unless you are comfortable sharing them with Felo. The publisher should remove or strictly validate the endpoint override and add an explicit data-sharing notice.
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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The README tells users to set an API key and use the tool, but it does not clearly disclose that user-supplied prompts will be transmitted to the external Felo Mindmap service. This creates a data-handling transparency issue: users may unknowingly send sensitive meeting notes, project plans, or proprietary content to a third party, which is especially relevant because the skill is explicitly designed around arbitrary user queries and LiveDoc content.
- Content
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
The skill instructs the agent to read an environment variable and make an outbound network request, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates a least-privilege violation: an agent/runtime may grant broader capabilities than intended, increasing the chance of unauthorized secret access or external data exfiltration if the skill is invoked in an unexpected context.
- Content