ClawHub
Back to skill

Security audit

remember-podcasts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow podcast-note search integration that clearly uses a remote BlueColumn/Supabase API, with privacy and credential-handling caveats users should understand.

Install only if you are comfortable sending podcast notes, timestamps, queue items, and search queries to BlueColumn's remote service. Do not store secrets, regulated data, or confidential internal notes unless that service is approved for your use, and keep the BlueColumn API key in a secure environment variable or secret manager.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs agents to transmit podcast notes, timestamps, and listening-history queries to a remote Supabase-hosted endpoint, but provides no warning about the sensitivity of that data or how it will be stored, retained, or shared. Even if the content seems low-risk, notes can contain private business strategy, personal interests, or confidential summaries, so silent external transmission creates a real privacy and data-governance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This example explicitly sends user-supplied podcast content to an external network endpoint using an authorization bearer token. The behavior is expected for the skill's purpose, but it is still security-relevant because it can exfiltrate sensitive notes or internal insights off-platform if used without consent and data-classification controls.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

Store the show, episode, date, and the ideas you want to keep — with timestamps.

bash
curl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-remember \
  -H "Authorization: Bearer $BLUECOLUMN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "POD: Acquired, \"Nvidia\" episode (Jul 2026). At 41:20 — the CUDA moat is ecosystem lock-in, not silicon. At 1:02:00 — Jensen on why they kept pricing high: \"no one ever died from too much margin\".", "title": "pod - Acquired Nvidia"}'

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill requires a live BlueColumn API key but does not include any guidance on secure credential handling. That omission increases the chance users will paste keys into logs, prompts, scripts, or shared environments, leading to accidental credential exposure and unauthorized API use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.