ClawHub
Back to skill

Security audit

Project Bootstrap

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local project bootstrap guide with no hidden code, persistence, or data exfiltration behavior.

This skill is reasonable to install for local project scaffolding. Before using it, confirm the target directory and review generated files and dependency choices, especially because the trigger metadata should be corrected from System.Object[] to explicit activation triggers.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
## Safety Rules
- Never modify global tooling on the machine unless explicitly requested.
- Pin versions where the repo requires it.
- Do not auto-deploy; bootstrap is local by default.

## Example
Bootstrap a TS backend:

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · project-bootstrap.md (reported line 45)May include surrounding context.

md
## Safety Rules
- Never modify global tooling on the machine unless explicitly requested.
- Pin versions where the repo requires it.
- Do not auto-deploy; bootstrap is local by default.

## Example
Bootstrap a TS backend:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest's triggers field is effectively unspecified and appears serialized as a generic object array type rather than concrete activation phrases or constraints. Ambiguous or malformed trigger definitions can cause the skill to activate unexpectedly or bypass intended user-scoping controls, increasing the chance of unintended execution in unrelated contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.