Security audit

Receipt Assistant

Security checks across malware telemetry and agentic risk

Overview

This is a coherent receipt-organizing skill that scans user-chosen receipt folders, copies renamed outputs, and creates Excel reports without evidence of hidden access, exfiltration, or destructive behavior.

Install only if you are comfortable letting the assistant process receipt images and PDFs in folders you choose. Confirm the input and output directories, review generated filenames and the Excel report before sharing them, and prefer a sandboxed or pinned-dependency environment for untrusted receipt files.

SkillSpector

By NVIDIA

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger phrases are broad common terms such as '报销', '发票', and '整理票据', which could match ordinary user conversation and invoke the skill unintentionally. Because the skill performs file scanning and renaming, accidental activation could lead to unwanted processing of local documents.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The workflow includes scanning directories, renaming files, and creating Excel reports, but the description does not clearly warn users that their files may be modified or new files written. Without an upfront warning and confirmation, users may unknowingly allow changes to important financial documents or metadata-bearing filenames.

Unpinned Dependencies

Low

Category: Supply Chain
Content: openpyxl>=3.1.0 pdfplumber>=0.10.0 Pillow>=10.0.0
Confidence: 96% confidence
Finding: The dependency is specified with a minimum version only, so installations may resolve to different later versions over time, including versions with newly introduced vulnerabilities or breaking changes. In a document-processing skill that parses untrusted spreadsheet and receipt files, dependency drift increases supply-chain risk and makes security review and reproducibility weaker.

Unpinned Dependencies

Low

Category: Supply Chain
Content: openpyxl>=3.1.0 pdfplumber>=0.10.0 Pillow>=10.0.0
Confidence: 95% confidence
Finding: Using an unpinned pdfplumber version allows non-deterministic installs and can pull in future releases or transitive changes that have not been security reviewed. Because this skill processes PDFs from users, parser dependencies are part of the attack surface and should be tightly controlled.

Unpinned Dependencies

Low

Category: Supply Chain
Content: openpyxl>=3.1.0 pdfplumber>=0.10.0 Pillow>=10.0.0
Confidence: 97% confidence
Finding: Pillow is declared as >=10.0.0, which permits a wide range of versions and weakens reproducibility and security assurance. Since the skill handles potentially untrusted image-based receipts, an image library with floating versions materially increases exposure to parser bugs and supply-chain issues.

Known Vulnerable Dependency: Pillow — 10 advisory(ies): CVE-2016-2533 (Pillow buffer overflow in ImagingPcdDecode); CVE-2023-50447 (Arbitrary Code Execution in Pillow); CVE-2021-27922 (Pillow Uncontrolled Resource Consumption) +7 more

Critical

Category: Supply Chain
Confidence: 88% confidence
Finding: Pillow has a history of serious vulnerabilities, including code execution and denial-of-service issues, and the requirement does not constrain the installation to a known-safe patched release. In this skill, users are expected to provide receipt images, making the image parser directly exposed to attacker-controlled inputs and increasing the practical risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.