Trust Assessment
beanstalk-gateway received a trust score of 54/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 7 findings: 0 critical, 2 high, 2 medium, and 1 low severity. Key findings include Missing required field: name, Sensitive path access: AI agent config, Unpinned npm dependency version.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 63/100, indicating areas for improvement.
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 Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/tommygeoco/beanstalk-gateway/scripts/setup.sh:18 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/tommygeoco/beanstalk-gateway/scripts/setup.sh:19 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/tommygeoco/beanstalk-gateway/SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency version Dependency 'ws' is not pinned to an exact version ('^8.18.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/tommygeoco/beanstalk-gateway/package.json | |
| LOW | Loose dependency versioning for critical component The 'ws' dependency in package.json uses a caret (^) version range ('^8.18.0'), allowing minor and patch updates. While package-lock.json pins the exact version ('8.19.0'), relying solely on package.json could lead to unexpected dependency updates if the lock file is not honored or regenerated, potentially introducing new vulnerabilities. For a critical network communication component, exact pinning in package.json is often preferred for maximum predictability. Consider pinning the 'ws' dependency to an exact version in package.json (e.g., "ws": "8.19.0") to ensure maximum predictability and prevent unintended updates, especially for critical network components. | LLM | package.json:9 | |
| INFO | Operational data transmitted to remote service The skill's primary function is to periodically fetch operational status from the local Clawdbot instance (e.g., agent status, model, active sessions, channel information, system uptime) and transmit this data to the remote 'beans.talk' server via WebSocket. This is an intended feature for remote monitoring and control. Ensure users are fully aware of the type of data being transmitted and to which third-party service. The skill's documentation (SKILL.md) explicitly states its purpose for 'remote monitoring and control', which provides this context. | LLM | scripts/gateway-client.js:80 | |
| INFO | Authentication token handled and transmitted The skill reads a 'GATEWAY_TOKEN' from environment variables or a local configuration file (.beanstalk/gateway.json) and uses it to authenticate with the remote WebSocket server. This token is transmitted over the WebSocket connection. This is a necessary part of the skill's functionality for secure communication with the 'beans.talk' service. Advise users to treat the GATEWAY_TOKEN as sensitive and ensure it is stored securely (e.g., with restricted file permissions for `gateway.json`). Verify that the WebSocket connection uses WSS (secure WebSocket) to protect the token in transit, as implied by the `wss://` examples in the setup instructions. | LLM | scripts/gateway-client.js:170 |
Scan History
Embed Code
[](https://skillshield.io/report/a804df8351cac20c)
Powered by SkillShield