ClawHub
Back to skill

Security audit

Software Engineer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only software engineering guidance skill with broad but disclosed scope and no evidence of hidden execution, data collection, persistence, or privilege escalation.

Install this if you want general coding guidance applied across many development tasks. Be aware that it may activate often for programming requests, so use a narrower skill for specialized high-risk work such as security-critical auth, payments, or infrastructure changes.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 6)May include surrounding context.

md
---
name: Software Engineer
slug: software-engineer
version: 1.0.0
homepage: https://clawic.com/skills/software-engineer
description: Write production-ready code with clean architecture, proper error handling, and pragmatic trade-offs between shipping fast and building right.
metadata: {"clawdbot":{"emoji":"👨‍💻","requires":{"bins":[]},"os":["linux","darwin","win32"]}}
---

## When to Use

Agent needs to write, review, or refactor code. Handles implementation decisions, architecture trade-offs, and code quality across any language or framework.

## Quick Reference

| Topic | File |
|-------|------|
| Code patterns | `patterns.md` |
| Architecture decisions | `architecture.md` |
| Testing practices | `test

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · architecture.md (reported line 52)May include surrounding context.

Environment-based:

text
.env.development    # Local defaults
.env.production     # Production values (never committed)
.env.example        # Template with dummy values (committed)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · architecture.md (reported line 53)May include surrounding context.

Environment-based:

text
.env.development    # Local defaults
.env.production     # Production values (never committed)
.env.example        # Template with dummy values (committed)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% 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 · architecture.md (reported line 93)May include surrounding context.

POST /users # Create PUT /users/:id # Replace PATCH /users/:id # Update DELETE /users/:id # Remove

text

**Response structure:**

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s activation scope is very broad: 'write, review, or refactor code' and 'across any language or framework' can cause it to trigger on a large share of normal development requests. Overly broad routing increases the chance of inappropriate delegation, where a powerful coding skill is invoked in contexts that may require narrower controls or a more specialized security-aware workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.