Back to skill

Security audit

AgentSearch Web Search (no API key, x402)

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a skill with disclosed search requests to external services and no executable scripts; the verdict is benign because the flagged network activity appears consistent with its search purpose, though the review is incomplete.

The verdict is benign with medium confidence, not a guarantee of no risk. Before installing, consider that using the search service sends queries to an external provider and may involve paid calls; the scanner excerpt says paid calls should be made only with the user’s payment setup and approval. Review the skill’s handling of your queries, and keep in mind that two local path-like references were unresolved, leaving the evidence incomplete.

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
  • 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 (3)

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 27)May include surrounding context.

Search (25 free searches per IP in total, then pay per call):

bash
curl -s -X POST https://relay.agentsearchhq.com/v1/search \
  -H 'content-type: application/json' -H 'x-agent-client: agentsearch-clawhub-skill/1.0.1' \
  -d '{"query":"openclaw web_search provider plugin","max_results":5}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 50)May include surrounding context.

md
Paid calls spend the user's money, so only make them when the user has set up their own x402 wallet or client and has approved paying per call (ideally with a spend cap in that client). Ask before the first paid call in a task and stay within any budget the user gives.

Base URL: `https://api.agentsearchhq.com/x402/v1/`. No account or API key: an unpaid POST returns HTTP 402 with x402 v2 payment requirements, and any x402-capable client or wallet pays and retries. Prices per call: search $0.003, news $0.003, extract $0.002, search_and_read $0.005, render $0.005, screenshot $0.004.

| Path | Body |
| --- | --- |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 61)May include surrounding context.

md
| `search_and_read` | `{"query": "...", "num_results": 3}` |
| `screenshot` | `{"url": "https://..."}` |

Discovery document: https://api.agentsearchhq.com/.well-known/x402 . Docs: https://agentsearchhq.com/docs/x402

## How to work