ClawHub
Back to skill

Security audit

ia-planning

Security checks across malware telemetry and agentic risk

Overview

This skill is a planning workflow that writes disclosed local planning files and does not show hidden, destructive, or exfiltrating behavior.

Install only if you want the agent to create and maintain `.plan/` working files in your project and update `.gitignore` to exclude them. Review the generated plan before choosing any execution handoff, especially if subagents are proposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The load condition says to use this file when "decomposing a plan into slices," "annotating phases," or "handing an approved plan off," which are broad workflow descriptions rather than specific trigger phrases or constrained contexts. It does not provide clear boundaries or negative examples for when this reference should not be loaded, increasing the chance of over-invocation in ordinary planning situations.

Hidden Instructions

High
Category
Prompt Injection
Content
Out of scope:
- Acting as the runtime instructions themselves (those live in `SKILL.md`).
- Trigger phrasings already covered by adjacent `ia-*` skills (`validate-plugin` flags >70% description overlap as DUPLICATE_TRIGGER).
- <!-- to fill in: domain-specific exclusions when the skill drifts -->

## Trigger Context
Confidence
70% confidence
Finding
<!-- to fill in: domain-specific exclusions when the skill drifts --> ## Trigger Context - Class: `workflow` - Hook regex: `plugins/whetstone/hooks/skill-patterns.sh` -> `SKILL_PATTERNS[ia-planning]

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.