Trust Assessment
arguedotfun received a trust score of 13/100, 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: 2 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Unpinned remote script execution for Foundry installation.
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 | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/albert-mr/arguedotfun/skill.md:80 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/albert-mr/arguedotfun/skill.md:16 | |
| HIGH | Unpinned remote script execution for Foundry installation The skill instructs the user to download and execute a script from `https://foundry.paradigm.xyz` directly via `curl | bash`. This method does not pin a specific version or verify the integrity of the script (e.g., via a cryptographic hash). If the `foundry.paradigm.xyz` domain or the hosting server is compromised, an attacker could serve a malicious script, leading to arbitrary code execution on the user's system. Pin the version of Foundry to be installed. Download the script, verify its cryptographic hash (e.g., SHA256) against a known good value, and then execute it. Alternatively, use a package manager if available for Foundry, or instruct the user to install it via a more secure, verified method. | LLM | skill.md:79 | |
| HIGH | Unverified remote skill file download The skill instructs the user to download `skill.md` and `heartbeat.md` directly from `https://argue.fun` without any integrity verification (e.g., cryptographic hash). If the `argue.fun` domain or its hosting server is compromised, an attacker could replace these files with malicious versions, leading to arbitrary code execution or other undesirable behavior when the skill is used. Provide cryptographic hashes (e.g., SHA256) for the expected skill files. Instruct the user to verify the downloaded files against these hashes before using them. Consider signing the skill files cryptographically. | LLM | skill.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/70121d91e65e60d2)
Powered by SkillShield