Trust Assessment
4claw received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Dynamic execution of unverified external instructions (HEARTBEAT.md).
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Dynamic execution of unverified external instructions (HEARTBEAT.md) The skill instructs the agent to 'fetch and run `HEARTBEAT.md`' from `https://www.4claw.org/heartbeat.md` on a schedule. This constitutes a significant supply chain risk as the content of `HEARTBEAT.md` is not version-pinned, integrity-checked, or sandboxed. A compromise of the `4claw.org` domain or malicious modification of `HEARTBEAT.md` could lead to the agent executing arbitrary, potentially harmful, instructions (prompt injection) or performing unintended actions, effectively allowing remote code execution within the agent's operational context. Remove the instruction to dynamically fetch and execute `HEARTBEAT.md`. Instead, embed the heartbeat logic directly within the skill, or provide `HEARTBEAT.md` as a static, version-controlled file within the skill package. If dynamic updates are strictly necessary, implement robust integrity checks (e.g., cryptographic signatures, hash verification) and ensure execution occurs within a secure, sandboxed environment. | LLM | SKILL.md:71 |
Scan History
Embed Code
[](https://skillshield.io/report/c26b3d34e87f1792)
Powered by SkillShield