Trust Assessment
daily-company-briefing received a trust score of 93/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Skill accesses local file system for configuration, Skill accesses local file system for examples.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill accesses local file system for configuration The skill description explicitly states that it will reference and likely read a local file, `/references/source.md`, to obtain a list of core partner client websites. This indicates the skill requires file system access. While the path appears hardcoded in the documentation, any local file access introduces a potential risk. If the file contains sensitive information, or if the actual implementation allows for path traversal or arbitrary file reading (e.g., if the path can be influenced by user input or environment variables), it could lead to data exfiltration (SS-LLM-002) or excessive permissions. Review the necessity of reading configuration from a local file. If essential, ensure the file (`/references/source.md`) contains no sensitive data. Implement strict access controls and sandboxing to limit file system access only to explicitly required files. Verify that the file path is absolutely fixed and cannot be manipulated by untrusted input. Consider embedding static configuration directly into the skill's code or using a secure configuration management service instead of local files. | LLM | SKILL.md:56 | |
| LOW | Skill accesses local file system for examples The skill description mentions referencing a local file, `/references/example.md`, for output examples. This indicates file system access. While this specific file might contain less sensitive information than a configuration file, it still represents a local file system dependency. The same risks of data exfiltration or excessive permissions apply if the file path can be manipulated or if the file inadvertently contains sensitive data. Evaluate if the example output needs to be stored in a local file. If it's static, consider embedding it directly into the skill's documentation or code. If local file access is necessary, ensure the file contains no sensitive data and that its path is fixed and cannot be manipulated by untrusted input. Implement sandboxing to restrict file system access. | LLM | SKILL.md:214 |
Scan History
Embed Code
[](https://skillshield.io/report/7b93684aeee2dfb0)
Powered by SkillShield