T09 · Insecure Skill Coding Practices
Warning
- Location
references/exa-mcp-setup.md:15- Finding
API Key Exposed Through MCP Endpoint Query String
- Content
View full analysis
- Remediation
View remediation
Security audit
Exa MCP
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small, coherent Exa research setup guide, with a credential-handling caution because it documents an API key in a URL query string.
Install only if you are comfortable configuring an Exa API key for hosted MCP access. Use a dedicated, limited Exa key if possible, keep MCP configs and logs private, and rotate the key if an expanded endpoint URL may have been copied into logs, diagnostics, or shared files.
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 (1)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The documentation places an API key in the URL query string for the MCP endpoint. Even though it uses an environment variable placeholder rather than a literal secret, query-string credentials are commonly exposed through logs, browser history, proxy telemetry, error reports, and shared configuration files, so the pattern creates a real credential-handling risk. In this skill context, the setup guidance is likely to be copied directly into client/server configs, which makes accidental leakage more likely.
- Content