Trust Assessment
tinman 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: 2 critical, 0 high, 4 medium, and 1 low severity. Key findings include Persistence / self-modification instructions, Unsafe deserialization / dynamic eval, Unpinned Python dependency version.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 33/100, 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 | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/oliveskin/agent-tinman/tinman_runner.py:353 | |
| CRITICAL | Persistence / self-modification instructions Windows registry Run key / hidden PowerShell Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/oliveskin/agent-tinman/tinman_runner.py:332 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/oliveskin/agent-tinman/tinman_runner.py:5 | |
| MEDIUM | Unpinned Python dependency version Requirement 'AgentTinman>=0.2.1' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/oliveskin/agent-tinman/requirements.txt:1 | |
| MEDIUM | Unpinned Python dependency version Requirement 'tinman-openclaw-eval>=0.3.2' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/oliveskin/agent-tinman/requirements.txt:2 | |
| MEDIUM | Unpinned Python dependency version Requirement 'pyyaml>=6.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/oliveskin/agent-tinman/requirements.txt:3 | |
| LOW | Unpinned Python Dependencies The skill's Python dependencies are specified with minimum versions (e.g., `AgentTinman>=0.2.1`, `pyyaml>=6.0`) rather than exact versions. This practice allows for automatic updates to newer versions, which could potentially introduce breaking changes or security vulnerabilities if a future version of a dependency is compromised or contains a bug. While common, it introduces a minor supply chain risk. Pin all Python dependencies to exact versions (e.g., `AgentTinman==0.2.1`) to ensure reproducible builds and prevent unexpected changes from upstream packages. Use a dependency management tool to manage and audit dependencies. | LLM | requirements.txt:1 | |
| INFO | Broad File System Access Permissions The skill requests broad 'read' and 'write' permissions for the file system. While these permissions are necessary for the skill's stated purpose as a security scanner (e.g., analyzing session traces, writing reports, and scanning files for sensitive data), they are inherently powerful and could be misused if the skill itself were compromised or contained a vulnerability. The skill does implement internal controls like the '/tinman check' command to gate access to sensitive files, and logs are sanitized to prevent data exfiltration. Ensure the skill's internal logic for handling file operations is robust and thoroughly audited. Consider if more granular file access permissions could be defined, or if the skill's operations can be confined to a specific directory within the workspace. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/a48e7bfc31fa979c)
Powered by SkillShield