Trust Assessment
api-patterns received a trust score of 87/100, 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, 0 high, 1 medium, and 2 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Unused broad permissions declared in manifest.
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 | |
| LOW | Unused broad permissions declared in manifest The skill's manifest declares 'Write', 'Edit', and 'Grep' permissions. However, the provided Python script `scripts/api_validator.py`, which is the only executable code in this skill package, only utilizes 'Read' and 'Glob' permissions (via `pathlib.Path.read_text` and `pathlib.Path.glob`). Declaring permissions that are not actively used by the skill's code grants unnecessary capabilities to the agent, increasing the potential attack surface if the skill's functionality were to change or if an attacker could somehow coerce the agent into attempting to use these unused permissions. Remove 'Write', 'Edit', and 'Grep' from the 'allowed-tools' declaration in the manifest, as they are not used by the current skill implementation. Only declare the minimum necessary permissions ('Read', 'Glob'). | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/c0f2216b55fb8098)
Powered by SkillShield