ClawHub
Back to skill

Security audit

ClawGrab

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign because its reported findings appear aligned with its purpose, though one dimension has a note and the scan evidence is incomplete.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable sending video URLs to the named transcription service. Skillspector’s analysis is partial: it reported two unresolved local path references, so the evidence is incomplete.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

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

md
- starts with `https://` or `http://`, and
- contains **no** spaces, quotes (`'` `"` or backtick), backslashes, `$`, `;`, `|`, `&&`, `<` or `>`.

If it fails this check, do not run any command. Ask the user for a clean, direct video link.
(This stops a malicious "link" from injecting shell commands.)

## Step 2 - grab the transcript (one request)

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 66)May include surrounding context.

bash
f=$(mktemp)
curl -sS --max-time 150 -X POST "https://getclawgrab.com/api/transcribe" \
  -H "Content-Type: application/json" \
  -H "User-Agent: clawgrab-clawhub-skill/1.0.1" \
  -d '{"url":"VIDEO_URL","options":{"clean":true}}' \