ClawHub
Back to skill

Security audit

rigorous-code-analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a plain coding guidance skill that promotes careful engineering work and does not add hidden execution, data collection, or persistence.

Install this if you want a broadly applicable skill that nudges coding work toward evidence, minimal changes, and verification. The main tradeoff is that its trigger is broad, so it may influence many routine software tasks rather than only specialized debugging or review 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
  • 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

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description says to use this skill when 'analyzing, debugging, modifying, reviewing, testing, or designing code,' which spans a very large share of ordinary software tasks without clear boundaries or exclusion conditions. Because SKILL.md is a markdown file and SQP-1 applies, this broad trigger scope could cause the skill to be invoked for many routine requests where more specific skill-selection criteria would be safer.

Content

No source excerpt is available for this finding.