ClawHub
Back to skill

Security audit

Craft Connect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Craft API helper, but users should protect its Craft Connect URL because it acts like a credential with read/write access.

Install only if you want your agent to manage the connected Craft space. Treat CRAFT_API_URL as a password, keep TOOLS.md private, do not commit it, scope broad searches where practical, and review delete, upload, and collection schema changes before execution.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly supports broad read/search operations over Craft documents, tasks, comments, and metadata, but it does not warn that user content will be transmitted to a remote Craft Connect endpoint. In this context, the omission matters because the skill can enumerate and retrieve potentially sensitive workspace data, increasing the chance of unintentional privacy exposure during normal use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The setup instructs users to store an authenticated API base URL containing an embedded link token in TOOLS.md, but it does not treat that value as a secret. Anyone or any process with access to TOOLS.md could reuse the URL to read or modify the connected Craft space, making credential leakage likely and impactful.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

md
curl -s "$CRAFT_API_URL/folders"

# List documents in a location (unsorted | trash | templates | daily_notes)
curl -s "$CRAFT_API_URL/documents?location=unsorted"

# List documents in a folder
curl -s "$CRAFT_API_URL/documents?folderId=<FOLDER_ID>"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 184)May include surrounding context.

bash
# Update (only provided fields change; others preserved)
curl -s -X PUT "$CRAFT_API_URL/blocks" \
  -H "Content-Type: application/json" \
  -d '{"blocks": [{"id": "<BLOCK_ID>", "markdown": "Updated", "font": "serif"}]}'

Static analysis

No suspicious patterns detected.