ClawHub
Back to skill

Security audit

Agent Daily Report

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill is a disclosed self-reporting template, but users should be aware it asks the agent to summarize session or daily activity on a default daily schedule.

Install this only if you want the agent to prepare daily summaries from its activity history. Review reports before sharing them outside your workspace, and consider adding your own rule to redact secrets, private filenames, customer data, and sensitive task details before any report is submitted.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly promises automatic daily report submission and states it will use execution logs or memory to generate the report, but it does not require explicit user consent at send time or warn that sensitive session activity may be included. This creates a real risk of unintended disclosure of prior actions, prompts, file names, or other sensitive work context through an automated outbound summary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instructions at the reporting schedule section mandate automatic generation and submission at 22:00, but they do not mention any privacy boundary, approval gate, or sensitivity filtering. In context, this is more dangerous because the skill's purpose is to summarize the agent's own execution history, which can easily expose confidential user requests, internal data sources, or security-relevant activity if reported automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description sets a default daily submission time at 22:00 in Asia/Shanghai, which imposes a locale-specific configuration on all users. The policy requires either user choice/opt-in or a clearly justified regional constraint, neither of which is provided here.

Content

No source excerpt is available for this finding.