ClawHub
Back to skill

Security audit

Log To Alert

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill converts user-provided logs into alert-rule drafts and shows no hidden persistence, credential handling, or automatic system changes.

Before installing, treat generated alert rules as drafts and avoid pasting logs that contain secrets or sensitive customer data unless you are comfortable having the agent process them. The included tests and contributor files appear QA-oriented and may be rough, but they do not add suspicious runtime authority.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This is a clear description-behavior mismatch. The declared purpose is an operational log-analysis skill for converting logs into alert conditions. The actual code chunk only implements automated tests for skill metadata and file structure. Its behavior is centered on QA/compliance checks against SKILL.md and repository contents, plus scanning for embedded secrets. No logic processes server/application logs, detects error patterns, or outputs structured alerts. The code's primary purpose is materially different from the declared description.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 12)May include surrounding context.

md
## What Problem This Solves

Recurring errors in logs keep appearing but nobody has time to manually create alert rules. This skill parses log entries, identifies error/warning patterns (≥3 occurrences = recurring), and outputs ready-to-use alert specs for Prometheus, Grafana, or PagerDuty.

**When triggered:** Log text + alert/monitor/create rule intent.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation description 'Log text + alert/monitor/create rule intent' does not define specific trigger phrases or clear boundaries for when the skill should activate. Terms like 'alert' and 'create rule' are broad and could overlap with ordinary discussion about monitoring rather than an intentional request to invoke this skill.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This Python test file contains a natural-language and behavioral requirement that the skill repository must include README_zh.md. That imposes a specific locale expectation in project policy without any visible opt-in, choice, or documented region-specific justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file explicitly requires contributors to keep the SKILL.md body in English. This is a natural-language locale policy constraint, and the document does not present it as an optional choice or a narrowly justified regional/compliance requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This line mandates that the SKILL.md body and reference docs must be in English. That is a language policy restriction affecting contributors, and no user choice or explicit justification is given in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This README is entirely written in Chinese and does not state within the document that users may choose another language or locale. Under the policy rule, forcing a specific language without explicit opt-in can be a natural-language policy violation, even though an English link is present.

Content

No source excerpt is available for this finding.