ClawHub
Back to skill

Security audit

skill-install-firewall

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently checks packages before installation and clearly discloses sending their contents to an external scanning service.

Use the hosted scan only for package contents you are authorized to share with the named provider, and remove live secrets before submission. The instructions describe MCP audits as paid. Review the evidence yourself; a clean scan does not guarantee safety.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
1. **Collect the artifact.** The skill directory (SKILL.md + scripts) or the
   MCP server's tool list. Never install first "to look at it".
2. **Local pass (free).** Grep for the classic tells: `curl | sh`, base64
   blobs piped to a shell, credential literals (`api_key=`, `token=`),
   env-var exfiltration, `sudo` inside skill scripts, network calls to
   non-declared hosts. Record file+line for each hit.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

md
**Ask:** "Install the `crypto-tips` skill from the marketplace for me."

**Before:** agent installs it; the skill ships an undeclared `curl | sh` and a
wallet-key regex; first run exfiltrates a key from the env.

**After:** local grep flags the pipe-to-shell line; the DDG scan returns

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The hosted scan instructs the agent to transmit complete skill and script contents to a third-party service, potentially disclosing embedded credentials or proprietary code. The destination and purpose are explicitly disclosed, and the warning against submitting live secrets reduces concern about malicious intent, but the workflow does not require a verified sanitization step or authorization before uploading.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

non-declared hosts. Record file+line for each hit. 3. Hosted pass (the part that catches declaration mismatch).

bash
curl -s -X POST https://agents.daedalusdevelopmentgroup.com/v1/ai-skill-safety-scan \
  -H 'content-type: application/json' -H "X-Agent-Id: $DDG_AGENT_ID" \
  -d '{"skill":"<name@version>","declared":"<what the manifest claims>","files":"<SKILL.md + scripts text>"}' \
  > out/scan.json

Static analysis

No suspicious patterns detected.