ClawHub
Back to skill

Security audit

ia-planning

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent software-planning skill that creates local plan files and does not show deceptive, destructive, or data-exfiltrating behavior.

Install this for planning-oriented software work if you are comfortable with it creating or updating local planning files and .gitignore entries. Review existing .plan/task_plan.md before using --force, and treat delegated execution guidance as applying only after you have authorized implementation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (3)

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
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Memory Manipulation

High
Category
Memory Poisoning
Content
2. Identify phases or tasks that are vague, under-specified, or missing verification steps
3. For each weak area, run targeted research (read relevant code, check existing patterns, verify assumptions)
4. Expand the weak sections with concrete file paths, code patterns, and verification steps
5. Preserve supported decisions; replace instructions contradicted by verified evidence. Keep useful superseded rationale in a separate decision-history note, not in the active execution steps.

Maintain one internally consistent current plan. Restructure only where needed to resolve a gap or contradiction, and report material decision changes.
Confidence
85% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The load condition says to use this file when 'decomposing a plan into slices,' 'handing an approved plan off to implementation,' or 'specifying behavior against an existing reference implementation,' which are broad situations rather than specific trigger phrases or constrained invocation criteria. Because it lacks exclusions or negative examples, the skill could be invoked in many ordinary planning conversations where its use may not be intended.

Static analysis

No suspicious patterns detected.