Security audit

Email Excel Transfer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent email-to-Excel helper, but it handles private mailbox data and reusable email credentials with weak scoping and unsafe examples.

Review this carefully before installing. Use a dedicated low-privilege mailbox or OAuth token, do not store real app passwords in source files, require the user to choose the account/message/sender before reading mail, make sender checks exact, and save attachments in a private temporary directory with size and file-type limits.

A.I.G

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 (4)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:47
Finding: Plaintext Email Credentials Embedded in Source Configuration
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:78
Finding: Sender Allowlist Bypass Through Substring Matching
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:93
Finding: Predictable Temporary File Creation Permits Symlink-Based Overwrite
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: SKILL.md:100
Finding: Weak Attachment Validation and Unbounded XLSX Archive Processing
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill name/description triggers on a very broad user intent around moving email data into Excel, without requiring clearer constraints such as source account, sender scope, attachment type, or explicit confirmation before accessing mailbox contents. In an agent environment, overly generic invocation can cause the skill to activate during ordinary conversation and perform sensitive email/file operations the user did not specifically intend.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The example phrase "pobierz dane z maila i wstaw do Excela" is generic enough to overlap with normal conversational requests, increasing the chance of accidental skill invocation. Because this skill accesses email and writes spreadsheet data, unintended activation could expose private mail content or alter files even if performed on copies.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description forces a single language/locale presentation and does not indicate any user choice or opt-in for language. This can violate language policy expectations when skills should not impose a locale without justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The whole skill guidance is presented in Polish, including safety instructions and invocation examples, but there is no statement that the user selected Polish or that the skill is region-specific. That creates a natural-language locale constraint without documented opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.