ClawHub
Back to skill

Security audit

Executive Summary

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides guidance for writing executive summaries and does not request unusual access or run code.

Installers should expect this skill to shape summaries for senior decision-makers. It is benign, though clearer negative examples could help prevent it from activating for ordinary summaries that are not meant to be executive briefs.

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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This markdown file includes example trigger phrases such as 'Summarise this document for the board' and 'Turn these findings into an exec summary' without clarifying when the skill should not activate. While the skill is generally domain-specific, the trigger section does not provide negative examples or scope constraints, which could allow overlap with general summarization requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.