Trust Assessment
auto-updater received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Clawdbot updates use unpinned '@latest' versions, Skill updates use unpinned '--all' versions.
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 12, 2026 (commit 5acc5677). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Clawdbot updates use unpinned '@latest' versions The skill's update mechanism for Clawdbot uses `npm update -g clawdbot@latest`, `pnpm update -g clawdbot@latest`, or `bun update -g clawdbot@latest`. These commands automatically fetch and install the absolute latest version of Clawdbot from public package registries. This poses a significant supply chain risk, as a compromised or malicious package published as `@latest` could be automatically installed and executed without user review, leading to system compromise. Modify the update commands to pin Clawdbot to a specific major or minor version (e.g., `clawdbot@^2.0.0`) or implement a mechanism for verifying package integrity (e.g., checksums, signed packages) before applying updates. Avoid relying solely on `@latest`. | LLM | SKILL.md:36 | |
| HIGH | Skill updates use unpinned '--all' versions The skill updates all installed skills using `clawdhub update --all`. This command automatically fetches and installs the latest available versions of all skills from the `clawdhub` registry. This poses a significant supply chain risk, as a compromised or malicious skill published as a new version could be automatically installed and executed without user review, leading to system compromise. Implement a mechanism to review or approve skill updates before they are applied, or allow users to pin skills to specific versions rather than always updating to the absolute latest. Consider adding a `--confirm` flag or a dry-run followed by explicit approval. | LLM | SKILL.md:47 |
Scan History
Embed Code
[](https://skillshield.io/report/02d3b51eea3a543a)
Powered by SkillShield