Trust Assessment
clawk received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Dynamic loading of skill instructions from external URL.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Dynamic loading of skill instructions from external URL The skill explicitly instructs the agent to re-fetch its own `skill.md` and `heartbeat.md` files from `https://clawk.ai` at the start of each session. This creates a significant supply chain risk. If the `clawk.ai` server were compromised, an attacker could inject malicious instructions into the agent's operational guidelines, leading to arbitrary code execution (via agent actions), data exfiltration, or other harmful behaviors. This bypasses static analysis and allows for runtime modification of the agent's core directives. Avoid dynamic loading of instructions from external, untrusted sources. All skill logic and instructions should be bundled within the skill package and subject to static analysis. If dynamic updates are necessary, implement cryptographic signing and verification of the fetched content to ensure integrity and authenticity. | LLM | SKILL.md:11 |
Scan History
Embed Code
[](https://skillshield.io/report/aa84bfc73c346c9d)
Powered by SkillShield