Back to skill

Security audit

multi-search-aisa

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AISA-backed search client that sends user queries to an external search API and does not show hidden persistence, credential theft, or destructive behavior.

Install only if you are comfortable sending your search queries, requested URLs, and AISA API credentials to AISA's API. Avoid using it for sensitive local credential access, private documents, or queries containing secrets unless that external processing is acceptable.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
## When NOT to Use

- Do not use this skill for browser-cookie extraction, passwords, Keychain access, or other local sensitive credential access.
- Prefer a different skill when the user request is outside this skill's domain.

## Capabilities

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares it needs an API key and invokes a Python client that will likely make outbound network requests, but it does not declare any explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and makes the skill harder to sandbox or review, increasing the chance of unintended environment-variable exposure or unauthorized network use.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest describes a skill for comprehensive multi-source search and synthesis across web, academic, Tavily, and synthesis layers. This file additionally provides an extract mode that retrieves raw page content from arbitrary URLs and a sonar mode that calls separate research/chat-style endpoints, which are broader capabilities than the stated multi-search orchestration purpose.

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/search_client.py (reported line 28)May include surrounding context.

python
from concurrent.futures import ThreadPoolExecutor, as_completed
from typing import Any

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


def get_api_key() -> str:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code explicitly sets the explanation language to "en" when calling the synthesis endpoint. That imposes a specific language/locale choice on users without opt-in or an alternative selection path, which matches the policy's language/locale violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest sets the skill language to "en" on L07, which is a natural-language locale constraint. There is no indication in this file that users can opt into another language or that the English-only setting is required for a documented region- or compliance-specific purpose.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

get_api_key() accesses AISA_API_KEY from the environment to authenticate outbound requests. While network access is expected for search, reading environment-stored secrets is a distinct capability not reflected in the manifest's purpose statement and may be considered broader than the user-facing description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.