Back to skill

Security audit

Web Search 9routers Backup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed backup web-fetch helper that uses a local 9Router endpoint and does not include hidden code, persistence, or unrelated access.

Install only if you use the local 9Router backup service. Keep NINEROUTER_KEY in the environment, do not paste it into prompts or logs, and confirm URLs you do not trust before fetching them.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

Example

bash
curl -X POST http://localhost:20128/v1/web/fetch \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $NINEROUTER_KEY" \
 -d '{"model":"exa","url":"https://example.com","format":"html","max_characters":0}'

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

md
## Red Flags — STOP

- Never hardcode the bearer token in commands or output — use `$NINEROUTER_KEY`
- Never fetch URLs from untrusted user input without confirmation (SSRF risk)

## Version