Trust Assessment
behavioral-modes 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 3 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Skill declares broad filesystem permissions without clear justification.
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 | |
|---|---|---|---|---|
| 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 | |
| INFO | Skill declares broad filesystem permissions without clear justification The skill's manifest declares `Read`, `Glob`, and `Grep` permissions. While these tools can be useful for certain tasks, the primary purpose of this skill, as described ('AI operational modes'), does not inherently require such broad filesystem access. This creates a potential attack surface where a malicious prompt injection or a future skill update could leverage these permissions to read arbitrary files, list directories, or search file contents, potentially leading to data exfiltration or information disclosure. Although the current skill content does not actively instruct the use of these permissions, their declaration makes them available. Review and restrict `allowed-tools` to only those strictly necessary for the skill's intended functionality. If the skill's purpose is purely behavioral definition, no filesystem access might be needed. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/1fe8e9f2248e1e6b)
Powered by SkillShield