Trust Assessment
session-logs 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 8 findings: 0 critical, 8 high, 0 medium, and 0 low severity. Key findings include Sensitive path access: AI agent config, Potential Command Injection via `rg` search pattern, Path Traversal and Data Exfiltration via unvalidated file paths.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 10/100, 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 Findings8
| 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/guogang1024/session-logs/SKILL.md: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/guogang1024/session-logs/SKILL.md:30 | |
| 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/guogang1024/session-logs/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/guogang1024/session-logs/SKILL.md:61 | |
| 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/guogang1024/session-logs/SKILL.md:86 | |
| 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/guogang1024/session-logs/SKILL.md:99 | |
| HIGH | Potential Command Injection via `rg` search pattern The skill provides an example `rg -l "phrase" ...` where "phrase" is expected to be user-controlled. If the LLM does not properly sanitize or quote user input for the `phrase` argument, a malicious user could inject shell commands (e.g., by breaking out of quotes or by leveraging `rg`'s `--exec` flag if the LLM is prompted to add flags). Ensure all user-provided input for `rg` patterns is strictly sanitized, escaped, and enclosed in single quotes. Explicitly disallow `rg` flags like `--exec` or other command execution options. Consider using a safer API that doesn't involve direct shell command construction for user-controlled inputs. | LLM | SKILL.md:80 | |
| HIGH | Path Traversal and Data Exfiltration via unvalidated file paths Multiple examples use placeholders like `<session>.jsonl` and `<agentId>` for file paths. If the LLM allows user input to directly populate these placeholders without strict validation, a malicious user could provide paths like `../../../../etc/passwd` or `../..` to read arbitrary files or access directories outside the intended session scope, leading to data exfiltration. Implement strict validation for all file path components (e.g., `<session>`, `<agentId>`) to ensure they are canonicalized, do not contain path traversal sequences (`..`), and are confined to the expected directory structure. Only allow known valid session IDs and agent IDs. | LLM | SKILL.md:48 |
Scan History
Embed Code
[](https://skillshield.io/report/88c480ee07d74043)
Powered by SkillShield