Back to skill

Security audit

ReceiptExtract - OCR, Photo/PDF to CSV

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it uploads user-selected receipt files to ReceiptExtract for parsing, with no hidden persistence or unrelated behavior found.

Before installing, understand that receipt images or PDFs you choose to process will be sent to ReceiptExtract and may include merchant, location, purchase, tax, and payment-related details. Use it only for receipts you are allowed to upload, keep the API token in an environment variable or secret manager, and be careful with bulk or recursive directory processing.

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
  • 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 (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill declares network access, environment-variable secret usage, and file handling behavior, but it does not define an explicit tool/permission scope such as allowed tools or permissions. That creates ambiguity about what execution capabilities the agent may exercise when running the workflow, increasing the risk of overbroad access or unintended actions in environments that rely on declarative scoping for enforcement.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs uploading receipt images and PDFs to a third-party API but does not clearly warn that receipts often contain sensitive personal, financial, location, and transaction data. Users may unknowingly transmit PII or confidential business information off-platform without informed consent, which can create privacy, compliance, and data-handling risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation instructs users to upload receipt images/PDFs to an external API but does not clearly disclose that potentially sensitive financial documents and extracted transaction data are sent to a third-party service. Receipts often contain personal, payment, location, and merchant data, so lack of an explicit privacy/data-sharing warning can lead to uninformed disclosure and improper handling in downstream automations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script sends receipt images/PDFs to a third-party API, and receipts commonly contain sensitive financial and personal data such as merchant history, timestamps, itemized purchases, loyalty identifiers, and partial payment information. Although external upload is core to the feature, the lack of an explicit user-facing warning/consent step creates a real privacy and data-handling risk because users may not realize local files are transmitted off-device to an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This line performs the actual network transmission of the receipt file body to an external endpoint. In this skill context, that behavior is expected, but it still constitutes a genuine data exfiltration surface because highly sensitive receipt documents are sent to a remote service without any additional safeguards such as consent flow, destination verification beyond a hardcoded URL, or minimization of uploaded content.

Content

Scanner excerpt · scripts/extract_receipt.py (reported line 72)May include surrounding context.

python
req.add_header("Content-Length", str(len(body)))

    try:
        with urllib.request.urlopen(req, data=body) as resp:
            raw = resp.read().decode("utf-8")
            return resp.status, json.loads(raw)
    except urllib.error.HTTPError as e: