TinkerClaw Agent Superpowers

• Outcome: Pass
• Latest audit: Sep 17, 2026 · 12:18 PM UTC
• Version: 1.1.2

Overview

This is an instruction-only engineering workflow skill whose broad behavioral guidance is disclosed and aligned with its purpose.

Install this if you want your agent to follow stricter coding discipline. Be aware it may make coding sessions more process-heavy by encouraging plans, sub-agents, commits, and fresh verification, and only copy the AGENTS.md section if you want those rules to persist across sessions.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Tool Parameter Abuse

High

• Category: Tool Misuse
• Confidence: 65% confidence

Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 253)May include surrounding context.

md

| Action Type           | Examples                                      | Rule           |
| --------------------- | --------------------------------------------- | -------------- |
| **Local, reversible** | Edit files, run tests, search code            | Proceed freely |
| **Hard to reverse**   | Force push, git reset --hard, drop tables     | Confirm first  |
| **External-facing**   | Push code, create PRs, send messages          | Confirm first  |
| **Destructive**       | Delete files/branches, rm -rf, overwrite work | Confirm first  |

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The description says to use the skill for 'coding tasks of any complexity,' 'debugging failures,' 'planning features,' and 'reviewing code,' which covers a very large share of normal engineering conversation. It does not give limiting conditions, explicit trigger phrases, or negative examples to clarify when the skill should not activate, making unintended invocation more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 86% confidence

Finding

The markdown instructs users to paste the rules into AGENTS.md 'to activate always-on behavioral rules,' but does not define scope boundaries or exceptions beyond the rule text itself. For a manifest/markdown-triggered skill, 'always-on' creates an unclear activation condition because it can apply across many unrelated interactions unless more specific constraints are stated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.