Trust Assessment
internal-comms received a trust score of 80/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Potential Path Traversal via LLM File Loading Instruction.
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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Path Traversal via LLM File Loading Instruction The skill explicitly instructs the LLM to 'Load the appropriate guideline file from the `examples/` directory'. If the underlying file loading mechanism, triggered by the LLM's interpretation of this instruction, does not implement robust path validation and sandboxing, an attacker could potentially craft an input (e.g., a malicious 'communication type') that causes the LLM to perform path traversal (e.g., `../../../../etc/passwd`). This could lead to the unauthorized reading and exfiltration of sensitive files outside the intended `examples/` directory. Implement strict path validation and sandboxing for any file loading operations performed by the LLM. Ensure that the LLM's file access is strictly limited to the intended `examples/` directory and cannot traverse upwards or access other system files. Consider using a dedicated, hardened file access API or tool that enforces these restrictions, rather than relying solely on the LLM's interpretation of file paths. | LLM | SKILL.md:18 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/276805bf327fdfa6)
Powered by SkillShield