Trust Assessment
lastfm received a trust score of 28/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 1 critical, 3 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Potential Command Injection via Unsanitized Parameters.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gumadeiras/lastfm/SKILL.md:8 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gumadeiras/lastfm/SKILL.md:8 | |
| HIGH | Potential Command Injection via Unsanitized Parameters The skill documentation provides `curl` examples where parameters like `artist`, `track`, `album`, and `tag` are directly interpolated into the URL. If an AI agent constructs these `curl` commands using untrusted user input for these parameters without proper sanitization (e.g., URL encoding or shell escaping), it could lead to command injection, allowing an attacker to execute arbitrary shell commands on the host system. The agent implementing this skill must ensure all user-provided input used in `curl` command parameters is properly URL-encoded and shell-escaped before execution. Prefer using a robust HTTP client library that handles parameter encoding automatically instead of raw shell commands. | LLM | SKILL.md:100 | |
| HIGH | API Key Exposure Over Insecure HTTP The skill documentation specifies `http://ws.audioscrobbler.com/2.0/` as the base URL and includes the `$LASTFM_API_KEY` directly in the URL query parameters for all requests. Transmitting an API key over unencrypted HTTP makes it vulnerable to interception by attackers on the network, leading to unauthorized access to the Last.fm API. The Last.fm API should ideally be accessed over HTTPS to encrypt sensitive information like API keys. If Last.fm supports HTTPS for this endpoint, the base URL should be updated to `https://ws.audioscrobbler.com/2.0/`. If HTTPS is not supported, users should be explicitly warned about the inherent insecurity of transmitting their API key in plain text. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/504ef6d808c84682)
Powered by SkillShield