ClawHub
Back to skill

Security audit

Tri courrier entrant

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed first-pass accounting email triage and does not show hidden, persistent, destructive, or exfiltrating behavior.

Install only for the intended accounting email workflow. Because it summarizes email metadata and attachment paths, avoid feeding unrelated private mail unless that is acceptable for your pipeline, and keep downstream steps scoped to accounting documents.

A.I.G

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

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description contains broad, natural-language triggers such as "dès qu'un mail arrive", "ce mail me concerne ?", and "tri d'un courrier reçu", which can cause the skill to be invoked in contexts beyond a deliberate accounting workflow. In an email-processing pipeline, over-broad activation increases the chance of unintended processing of unrelated or sensitive messages, exposing metadata and attachments to downstream automation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The natural-language instructions, usage description, and behavior notes in the file are presented exclusively in French, with no indication that users may choose another language. This creates a language policy issue because the skill appears to require a specific language rather than offering a choice or documenting a justified locale restriction.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This code ingests and processes email content and metadata that can contain sensitive personal or business information, then prints a normalized summary including sender, subject, message ID, and attachment paths. Although the module docstring describes the input/output structure, there is no explicit user-facing warning or disclosure that sensitive email data will be read and emitted.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.