ClawHub
Back to skill

Security audit

AIsa Perplexity Sonar Search

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward AIsa search skill that sends user-provided research queries to AIsa's API using an API key, with no evidence of hidden persistence, local data scraping, or destructive behavior.

Before installing, confirm you trust AIsa with the research queries you submit and with the AISA_API_KEY used for access. Do not include passwords, private customer data, or confidential internal instructions in queries or the optional system prompt unless your data policy allows sending them to AIsa.

A.I.G

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

SkillSpector

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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill declares access to an API key and is designed to perform web-backed research, which implies environment and network capabilities, but it does not define any explicit tool scope such as permissions or allowed-tools. This creates an authorization ambiguity: a hosting agent may permit broader execution than intended, increasing the risk of unintended outbound requests, secret exposure, or misuse of network-capable code paths.

Content

No source excerpt is available for this finding.

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 · scripts/perplexity_search_client.py (reported line 25)May include surrounding context.

python
class PerplexitySearchClient:
    """Minimal client for AIsa Perplexity Sonar endpoints."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The client sends the user's query and optional system instruction directly to a third-party remote API, which can expose sensitive prompts, internal instructions, or proprietary data if users are not clearly informed. In a research/search skill, users may paste confidential business context or credentials into prompts, so silent external transmission creates a real data leakage risk even though the network call is the intended function.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.