ClawHub
Back to skill

Security audit

Proposal and Cover Letter Interviewer & Improver (Continuous Questions and Memory for Better Proposals/Cover Letters by Getting to Know You)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed proposal-writing interview workflow that stores user-provided professional facts locally, with privacy considerations users should understand before using it.

Install only if you are comfortable keeping proposal-related personal and company facts in local files under the skill folder. Review the stored files periodically, avoid sharing sensitive details unless needed, and be especially deliberate before scheduling recurring sessions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly directs collecting and storing detailed personal and company information on disk inside the skill folder, but it does not clearly warn the user about retention, visibility, access control, or privacy consequences. Because the data categories include personal history, work patterns, locations, relationships, and company details, users may disclose sensitive information without informed consent, increasing risk of privacy leakage or secondary misuse.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The cron-job section encourages recurring background use of the skill to continue learning about a person and building a statement library, but it does not prominently disclose that future scheduled runs may repeatedly collect and persist additional personal data. This creates a consent and transparency problem: users may not realize that ongoing automation can expand the profile over time, especially if triggered outside an active interactive session.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.