Back to skill

Security audit

ValueSERP Rank Checker

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims: it checks Google ranking through ValueSERP using a disclosed API key, with some quota and accuracy caveats.

Install this only if you intend to use a ValueSERP account for SEO ranking checks. Keep the API key limited to that service, use modest page counts to avoid quota or cost surprises, and specify country/language when Colombia Spanish is not the intended market.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/check_rank.py:87
Finding

Unbounded Pagination Can Exhaust API Quota and Resources

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/check_rank.py:55
Finding

Substring-Based Domain Comparison Produces False Ranking Matches

Content
View full analysis
Remediation
View remediation
str: value = value.strip().lower().rstrip(".") if not value: raise ValueError("Domain must not be empty") parsed = urllib.parse.urlsplit( value if "://" in value else f"//{value}" ) hostname = parsed.hostname if not hostname: raise ValueError("Invalid domain") hostname = hostname.encode("idna").decode("ascii").rstrip(".") if hostname.startswith("www."): hostname = hostname[4:] return hostname target_host = normalize_hostname(domain) result_host = normalize_hostname(result_domain) if result_host == target_host or result_host.endswith("." + target_host): ... ``` Further hardening should include: - Reject empty domains, paths without hostnames, credentials, invalid labels, and unexpected ports. - Decide explicitly whether subdomains should count as matches. - If registrable-domain matching is intended, use a maintained Public Suffix List implementation rather than substring matching. - Add tests for `example.com` versus `notexample.com`, `sub.example.com`, empty input, mixed case, trailing dots, and internationalized domains. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Tainted flow: 'url' from os.environ.get (line 34, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/check_rank.py (reported line 17)May include surrounding context.

python
def fetch_json(url: str) -> dict:
    with urllib.request.urlopen(url, timeout=30) as response:
        return json.loads(response.read().decode())

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

La skill requiere acceso a red y a una variable de entorno sensible (VALUESERP_API_KEY), pero no declara explícitamente el alcance de herramientas o permisos permitidos. Esa omisión debilita el principio de mínimo privilegio y dificulta la revisión de seguridad, porque un ejecutor podría conceder capacidades más amplias de las necesarias sin una política visible en el manifiesto.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

La descripción de activación incluye frases amplias como 'o cualquier consulta sobre posicionamiento SEO de un dominio en Google', lo que puede hacer que la skill se invoque en contextos no específicos o ambiguos. Esto aumenta el riesgo de ejecución innecesaria con acceso a red y secretos, además de enviar consultas a un tercero cuando quizá no era la intención exacta del usuario.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

La skill fuerza por defecto Google Colombia (gl=co) y español (hl=es) sin consentimiento explícito del usuario. Aunque no es una vulnerabilidad severa por sí sola, puede provocar resultados engañosos, fuga innecesaria de contexto regional al proveedor externo y decisiones erróneas si el usuario esperaba otra geografía o idioma.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The function signature hard-codes hl='es', and the CLI help also presents Spanish as the default language. This creates a language/locale policy issue because the skill defaults to a specific language rather than offering a neutral default or requiring explicit user choice, and no region-specific justification is documented.

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/check_rank.py (reported line 22)May include surrounding context.

python
def check_rank(keyword: str, domain: str, api_key: str, gl: str = "co", hl: str = "es", max_pages: int = 10):
    base_url = "https://api.valueserp.com/search"
    results_per_page = 10

    for page in range(1, max_pages + 1):