Trust Assessment
analytics-tracking received a trust score of 90/100, 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, 2 medium, and 0 low severity. Key findings include LLM instructed to read local file for context, LLM instructed to read local tool registry and integration files.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, static_code_analysis, dependency_graph. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 16, 2026 (commit a04cb61a). 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 | LLM instructed to read local file for context The skill explicitly instructs the LLM to read the content of `.claude/product-marketing-context.md` from the local filesystem. While intended for providing context, this direct file access by an untrusted skill could lead to data exfiltration if the file contains sensitive information and the LLM is not strictly prevented from incorporating such information into its output. Avoid instructing the LLM to directly read local files. Instead, provide necessary context directly within the skill definition or through a secure, sandboxed mechanism that explicitly controls what information can be accessed and how it can be used. | Unknown | SKILL.md:8 | |
| MEDIUM | LLM instructed to read local tool registry and integration files The skill instructs the LLM to reference (read) local files such as `../../tools/REGISTRY.md` and specific tool integration guides (e.g., `../../tools/integrations/ga4.md`). This direct file access, even for 'implementation' context, poses a risk of data exfiltration if these files contain sensitive information and the LLM is not strictly prevented from incorporating such information into its output. Avoid direct LLM access to local files. Provide necessary tool information directly within the skill or via a controlled, secure mechanism that explicitly controls what information can be accessed and how it can be used. | Unknown | SKILL.md:189 |
Scan History
Embed Code
[](https://skillshield.io/report/00b87ea1f4adb00b)
Powered by SkillShield