ClawHub
Back to skill

Security audit

project-specification

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a specification-writing workflow, but it forces an automatic handoff into a separate planning skill without asking the user first.

Install this only if you want an automated specification-to-planning workflow. If you only want a specification document, invoke it with --standalone or explicitly tell the agent to stop after the specification before it begins.

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
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:48
Finding

Mandatory Unconfirmed Delegation to an Unaudited Planning Skill

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill mandates automatic continuation into the next phase and explicitly suppresses user confirmation, which can cause the agent to perform additional actions beyond the user’s immediate request. In an agent workflow, this weakens user control and can lead to unintended file changes, planning actions, or cascading execution of other skills without an explicit opt-in at the transition point.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The instruction 'Do NOT prompt the user for confirmation' removes an important safety checkpoint before triggering a new workflow phase. This is dangerous because it authorizes autonomous decision-making and follow-on action without validating current user intent, increasing the risk of scope creep and unintended downstream operations.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
- `docs/specification.md` does not exist or is empty (phase failed)
- User explicitly requests to stop after specification

**Do NOT prompt the user for confirmation** — this is a lightweight checkpoint, not an interactive gate. The user can always interrupt if needed.

## Related Skills

Static analysis

No suspicious patterns detected.