Trust Assessment
clawdscan 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 Path Traversal in Session Inspection.
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 | Path Traversal in Session Inspection The `inspect` command allows a user-provided `session_id` to be used directly in constructing a file path. This can lead to path traversal, enabling an attacker to read arbitrary files outside the intended session directory by providing a `session_id` like `../../../../etc/passwd`. Sanitize the `session_id` input to prevent path traversal characters (e.g., `..`, `/`). Alternatively, after constructing the `filepath`, ensure that its resolved path (`filepath.resolve()`) is a subpath of the expected `session_dir.resolve()` before attempting to read the file. | LLM | clawdscan.py:700 |
Scan History
Embed Code
[](https://skillshield.io/report/62a238f78bef1d86)
Powered by SkillShield