Trust Assessment
clawdsense received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 2 critical, 2 high, 3 medium, and 0 low severity. Key findings include Arbitrary command execution, Potential hardcoded secret (high entropy), Sensitive path access: AI agent config.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 48/100, 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 | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Node.js child_process require Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/snail3d/voice-devotional/clawdsense-skill/scripts/health-monitor.js:10 | |
| CRITICAL | Hardcoded API Key Fallback The `analyzer.js` script includes a hardcoded Groq API key as a fallback if the `GROQ_API_KEY` environment variable is not set. This poses a critical security risk as the key could be exposed if the code is compromised, logged, or accidentally committed to a public repository. Even if intended as a placeholder, its direct use in code makes it a vulnerability that could lead to unauthorized API access. Remove the hardcoded fallback API key. Ensure the `GROQ_API_KEY` environment variable is always set before running the script. If a default is absolutely necessary for development, use a non-functional placeholder or a key with minimal permissions, and ensure it's never used in production. | LLM | scripts/analyzer.js:12 | |
| 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/snail3d/voice-devotional/clawdsense-skill/SKILL.md:34 | |
| HIGH | Arbitrary File Upload to User's Home Directory The `media-receiver.js` service allows unauthenticated clients to upload arbitrary files to a directory within the user's home directory (`~/.clawdbot/media/inbound`). While the filename is randomized, the extension is derived from the original filename or mimetype. An attacker could upload malicious files (e.g., scripts, configuration files, or large files to cause a denial of service) which could then be accessed, processed, or potentially executed by other parts of the system or the user. This grants excessive write permissions to an untrusted network endpoint. Implement stricter validation for uploaded files, including content type checking (e.g., using a library like `file-type` to verify actual file magic numbers, not just extensions/mimetypes). Consider storing uploads in a more isolated, temporary directory outside the user's home, or in a dedicated sandbox. Restrict allowed file types to only those explicitly needed (e.g., `image/jpeg`). Implement authentication for the upload endpoints. | LLM | scripts/media-receiver.js:27 | |
| MEDIUM | Potential hardcoded secret (high entropy) A high-entropy string (entropy=4.99) was found in a credential-like context. Verify this is not a hardcoded secret. Use environment variables for sensitive values. | Static | skills/snail3d/voice-devotional/clawdsense-skill/SKILL.md:71 | |
| MEDIUM | Potential hardcoded secret (high entropy) A high-entropy string (entropy=4.99) was found in a credential-like context. Verify this is not a hardcoded secret. Use environment variables for sensitive values. | Static | skills/snail3d/voice-devotional/clawdsense-skill/SKILL.md:75 | |
| MEDIUM | Automatic Exfiltration of Uploaded Images to Third-Party API The `analyzer.js` script automatically reads and base64-encodes *any* JPEG image found in `~/.clawdbot/media/inbound` and sends it to the Groq Vision API (`api.groq.com`) for analysis. Combined with the arbitrary file upload vulnerability in `media-receiver.js`, this creates a data exfiltration path. If an attacker can upload sensitive images (e.g., personal photos, confidential documents disguised as images) to this directory, they will be automatically sent to a third-party service without explicit user consent for each specific image. Implement explicit user confirmation or a whitelist mechanism before sending potentially sensitive images to external APIs. Ensure that only images explicitly intended for analysis are placed in the inbound directory. Strengthen the file upload validation in `media-receiver.js` to prevent non-image files or malicious images from being stored. | LLM | scripts/analyzer.js:20 |
Scan History
Embed Code
[](https://skillshield.io/report/7c41597fcc7da2cf)
Powered by SkillShield