Trust Assessment
llmwhisperer 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 11 findings: 5 critical, 5 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, User-provided file content transmitted to external API.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, 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 Findings11
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gumadeiras/llmwhisperer/SKILL.md:8 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gumadeiras/llmwhisperer/SKILL.md:10 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gumadeiras/llmwhisperer/SKILL.md:32 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gumadeiras/llmwhisperer/SKILL.md:34 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gumadeiras/llmwhisperer/SKILL.md:39 | |
| 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/gumadeiras/llmwhisperer/SKILL.md:8 | |
| 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/gumadeiras/llmwhisperer/SKILL.md:10 | |
| 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/gumadeiras/llmwhisperer/SKILL.md:32 | |
| 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/gumadeiras/llmwhisperer/SKILL.md:34 | |
| 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/gumadeiras/llmwhisperer/SKILL.md:39 | |
| MEDIUM | User-provided file content transmitted to external API The skill uploads the full binary content of the user-specified input file (`$1`) to a third-party API endpoint (`https://llmwhisperer-api.us-central.unstract.com`). While this is the intended functionality for text extraction, users should be explicitly aware that any file provided to this skill, including potentially sensitive documents, will be transmitted off-device to an external service. This constitutes a data exfiltration vector for user-controlled data. Ensure that the skill's documentation prominently and unambiguously informs users about the transmission of their file content to an external service. Consider adding an explicit confirmation prompt before uploading files, especially if the file path suggests sensitive content (e.g., `/etc/passwd`, `~/.ssh/id_rsa`). | LLM | scripts/llmwhisperer:24 |
Scan History
Embed Code
[](https://skillshield.io/report/56f4d8567b56a3a6)
Powered by SkillShield