Superlore Personal Podcast

• Outcome: Review
• Latest audit: Sep 16, 2026 · 10:23 AM UTC
• Version: 1.0.0

Overview

The skill is mostly coherent for connecting OpenClaw to Superlore, but its helper can send credentials to server-supplied absolute URLs without validating the destination.

Review before installing. The skill's main behavior is disclosed and useful for Superlore users, but the bundled helper should validate credential-bearing URLs against the expected Superlore HTTPS origin before sending tokens. If used, approve only minimal scopes and know how to revoke or rotate the Superlore agent credential.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

• Location: scripts/superlore.mjs:54

Finding

Authentication Credentials Can Be Sent to Server-Controlled Arbitrary URLs

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (9)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md

node scripts/superlore.mjs pair --code 123456 --scopes episodes:create,sources:read

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md

node scripts/superlore.mjs pair --code 123456 --scopes episodes:create,sources:read

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md

node scripts/superlore.mjs pair --code 123456 --scopes episodes:create,sources:read

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md

node scripts/superlore.mjs pair --code 123456 --scopes episodes:create,sources:read

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md

node scripts/superlore.mjs pair --code 123456 --scopes episodes:create,sources:read

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md

node scripts/superlore.mjs pair --code 123456 --scopes episodes:create,sources:read

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence

Finding

The skill invokes a bundled Node helper that uses network access and environment/token handling, but the manifest does not declare any explicit tool permissions or allowed-tools boundaries. That mismatch weakens least-privilege controls and can let an agent use capabilities users or the platform did not clearly consent to, especially around credential storage and external API access.

Content

No source excerpt is available for this finding.

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 88% confidence

Finding

The skill is explicitly designed for recurring use and persistent storage of an agent credential at ~/.config/superlore/agent.json or via an environment variable, creating session persistence across runs. Persistent authentication to a private podcast service increases the blast radius of host compromise or cross-skill misuse, particularly because the token grants access to private feeds, uploads, and possibly saved Sources.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md

---
name: "superlore-personal-podcast"
description: "Pair OpenClaw with Superlore to create or upload private podcast episodes and use saved Sources."
homepage: https://superlore.ai/integrations/openclaw
---

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 80% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

text

4. Tell the user the agent has claimed the code and is waiting for approval. The helper polls for approval, stores the one-time credential privately, acknowledges delivery, and performs a side-effect-free connection test.
5. If pairing expires or returns 401, ask for a new code. Never ask the user to paste a raw `slc_` credential.

## Create an episode