Back to skill

Security audit

Google Search API - Organic SERP, Knowledge Graph, PAA, AI Overview

Security checks for vulnerabilities and agentic risk

Overview

This skill provides clearly disclosed web search through Scavio, with routine privacy and API-key handling precautions.

Scavio receives submitted search queries, so remove secrets and unnecessary confidential details. Store your API key securely and prefer Authorization headers over URL parameters. Requests consume credits. The scanner’s reference gaps were resolved through inspection; downloaded dependencies and provider data retention remain outside this review.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

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 57)May include surrounding context.

Endpoint

text
POST https://api.scavio.dev/api/v2/google
Authorization: Bearer $SCAVIO_API_KEY

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 104)May include surrounding context.

md
API_KEY = "sk_your_key_here"

response = requests.post(
    "https://api.scavio.dev/api/v2/google",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={"query": "langchain agents tutorial", "gl": "us", "hl": "en"},
)

The workflow sends user queries to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The skill directs agents to send user queries to Scavio whenever current information is needed, without requiring sensitive-data minimization or checking authorization to share confidential content. Although third-party search is the advertised functionality and the provider is identified, automatic query construction could disclose private information unnecessarily.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 103)May include surrounding context.

md
# store in real code - keep it out of source control.
API_KEY = "sk_your_key_here"

response = requests.post(
    "https://api.scavio.dev/api/v2/google",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={"query": "langchain agents tutorial", "gl": "us", "hl": "en"},

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 103)May include surrounding context.

md
# store in real code - keep it out of source control.
API_KEY = "sk_your_key_here"

response = requests.post(
    "https://api.scavio.dev/api/v2/google",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={"query": "langchain agents tutorial", "gl": "us", "hl": "en"},

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The destination is legitimate for the skill, but the migration example puts the API key in the URL query string. Real keys used this way can persist in request logs, traces, or copied URLs, enabling unauthorized API use and credit consumption; HTTPS does not prevent those retention paths, although the documentation's preference for header authentication reduces the concern.

Content

Scanner excerpt · SKILL.md (reported line 146)May include surrounding context.

When the user has existing Custom Search JSON API code (googleapis.com/customsearch/v1, cse().list(...), a cx engine id, parsing items[]), do not rewrite it to the call above. Scavio answers the same request at Google's own path, so the migration is a host and key swap:

text
GET https://api.scavio.dev/customsearch/v1?key=%2A%2A%2A&cx=anything&q=coffee
  • Same parameters (q, num 1-10, start 1-based, gl, hl, lr, cr, safe, dateRestrict, siteSearch, siteSearchFilter, exactTerms, excludeTerms, orTerms, hq, fileType) and the same customsearch#search response: items[].title/link/snippet/displayLink/htmlTitle/htmlSnippet, searchInformation.totalResults (a string) and queries.nextPage.