Security audit

Tyche Pro — Full Invoice & Payment Intelligence

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to do invoice reporting locally, but its setup and export behavior need review before use.

Review before installing. Use a virtual environment instead of the provided system-level pip command, avoid running setup as an administrator, and store generated reports only in a private folder. Treat exported CSVs as sensitive billing data and be careful opening exports from invoice data you do not fully control.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:100
Finding: Unpinned Dependency Installation Bypasses Managed Python Environment Protections
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:324
Finding: Spreadsheet Formula Injection in the Analytics CSV Export
Content: View full analysis
.csv`. 4. A user opens the generated CSV in spreadsheet software. 5. The spreadsheet interprets the attacker-controlled cell as a formula rather than literal text. 6. Depending on spreadsheet capabilities and security settings, the formula may initiate external requests, disclose cell data, present decept ...[truncated 679 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The embedded code automatically writes a markdown report and CSV analytics export containing client names, emails, invoice status, amounts, and overdue information to local files without prominently warning users. In multi-user systems, shared workspaces, synced folders, backups, or CI/agent environments, these artifacts can persist and expose sensitive billing data beyond the user's expectations.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The security section states that all data stays on the machine and there is 'No transmission, no cloud' (L081-L083), presenting the skill as entirely local. However, the setup and manifest documentation require obtaining a LICENSE_KEY from ko-fi/openclaw-related external services (L015-L017, L089-L092), so the documentation overstates the skill's independence from external services. While the code itself does not transmit data, the documentation's absolute claim contradicts the operational dependency it describes.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.