ClawHub
Back to skill

Security audit

Video Searching

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed video-search helper that sends user queries to Memories.ai and does not show hidden persistence, local data harvesting, destructive behavior, or deception.

Install this only if you are comfortable using a Memories.ai API key and sending video-search queries to that service. Prefer explicit /video_search use for clarity, and be aware that the packaged script path or executable permissions may need correction for the skill to run reliably.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill invokes a shell runner script but does not declare any explicit tool scope such as allowed-tools or permissions. That creates an overbroad execution surface where a caller or hosting framework may permit shell access more generally than intended, reducing isolation and making command-executing behavior harder to audit and constrain. In this context, the risk is amplified because the skill accepts user-derived query input and passes it into a script invocation flow.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill's free-form trigger condition is broad enough to activate on general requests about sourcing, trends, creators, or brands whenever concrete video links are desired, without clear exclusion boundaries. Overbroad activation can cause the agent to invoke shell-backed external API workflows unexpectedly, increasing the chance of unintended data disclosure, unnecessary credential use, or execution in contexts where the user did not explicitly consent to this skill. The danger is higher here because activation leads to authenticated outbound requests using an API key.

External Transmission

Medium
Category
Data Exfiltration
Content
HTTP_CODE_FILE=$(mktemp)

{
  curl -sS -N -w "%{http_code}" \
    -H "Content-Type: application/json" \
    -H "Authorization: ${MEMORIES_API_KEY}" \
    -d "$BODY" \
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.