T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:16- Finding
Last.fm API Key and Listening Data Transmitted Over Cleartext HTTP
- Content
View full analysis
- Remediation
View remediation
Security audit
Last.fm
Security checks for vulnerabilities and agentic risk
Overview
This Last.fm skill is purpose-aligned, but it documents sending the user's API key and listening data over unencrypted HTTP.
Review before installing. Use HTTPS for Last.fm API calls, avoid exposing the expanded URLs in logs, use a dedicated Last.fm API key, and only configure an account whose listening history and profile stats you are comfortable querying through this skill.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (1)
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 (2)
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 99% confidence
- Finding
The documented base URL and all example curl commands use plain HTTP rather than HTTPS, which exposes requests to interception or modification in transit. Even if the API key is not highly privileged, plaintext transport can leak the user's Last.fm username, API key, listening queries, and returned personal data, and enables man-in-the-middle tampering of responses.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill documentation encourages querying user-specific Last.fm endpoints using a username and API key, but it does not clearly warn that listening history, profile statistics, and related metadata are sent to an external third-party service. In this context, the omission can mislead users about the privacy implications of using the skill, especially because the data relates to personal behavioral history and profile information.
- Content
Static analysis
No suspicious patterns detected.