Back to skill

Security audit

India ID Check (Aadhaar, PAN, IFSC, UPI & more)

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report undeclared online lookups that send supplied IFSC or PIN values to third parties, and redaction coverage gaps; inspection was partial.

Consider the reported privacy and redaction limitations before installing. If you use it, avoid lookup commands unless you are comfortable sending the supplied IFSC or PIN to the named external services, and do not assume redaction covers every advertised identifier type. The scan is incomplete because one local reference could not be resolved, so the findings do not establish that all behavior was reviewed.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description explicitly presents the skill as offline, but lookup() performs outbound HTTP requests using urllib.request.urlopen and transmits user-supplied IFSC or PIN values to third-party services. These requests occur only when the lookup command is invoked; ordinary validation, masking, detection, redaction, and cross-checking remain local. Nevertheless, the externally accessed resources and online capability are not disclosed in the declared purpose, constituting a clear mismatch. The supplied code does not show unrelated data collection or automatic transmission of other identifiers.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.

md
# India ID Check

Offline validation and decoding of Indian identifiers, plus privacy-safe masking and redaction. **Never judge an ID by eye or recompute checksums in your head — run the script.**

Script: `scripts/idcheck.py` (Python 3, standard library only). Input: a JSON string or a `.json` file. Output: JSON.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Redaction does not cover several identifier types advertised by the manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The redaction patterns omit supported identifier types, including driving licences and TANs, so text containing them can be returned unchanged without a coverage warning. Because the skill promotes redaction before storing or sharing personal data, callers may mistakenly treat that output as sanitized and disclose identifiers.

Content

No source excerpt is available for this finding.

The skill advertises offline operation but exposes an online lookup command that sends supplied identifiers to third parties.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest describes the skill as operating offline, but lookup() sends IFSC values to ifsc.razorpay.com and PIN codes to api.postalpincode.in. Although the code documentation labels this command optional and online, the manifest does not disclose this exception to its offline guarantee.

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/idcheck.py (reported line 555)May include surrounding context.

python
return {"ifsc": code, "source": "ifsc.razorpay.com", **{k.lower(): j.get(k) for k in keys}}
        if d.get("pin"):
            pin = re.sub(r"\D", "", str(d["pin"]))
            with urllib.request.urlopen(f"https://api.postalpincode.in/pincode/{pin}", timeout=15) as r:
                j = json.loads(r.read())[0]
            pos = j.get("PostOffice") or []
            return {"pin": pin, "source": "api.postalpincode.in", "status": j.get("Status"),