Trust Assessment
brainstorming received a trust score of 76/100, 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, Skill requests broad filesystem and Git access.
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 | Skill requests broad filesystem and Git access The skill explicitly instructs the LLM to perform actions that require broad access to the project's filesystem and Git repository. Specifically, it directs the LLM to 'Check out the current project state first (files, docs, recent commits)' (implying read access), 'Write the validated design to `docs/plans/YYYY-MM-DD-<topic>-design.md`' (implying write access), and 'Commit the design document to git' (implying Git command execution). It also suggests using a 'superpowers:using-git-worktrees' skill, which further implies Git interaction. If the agent's execution environment grants these capabilities without strict sandboxing, user confirmation, or fine-grained scope limitations, it could lead to unauthorized data modification, deletion, or information disclosure within the project. Implement strict sandboxing for file system and Git operations. Require explicit user confirmation for all write and commit actions. Limit file system access to specific, whitelisted directories. Use dedicated, scoped tools or APIs for Git interactions instead of direct shell access, ensuring that commands are properly sanitized and validated. | LLM | SKILL.md:41 | |
| 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/45cb9aabc17b1fb1)
Powered by SkillShield