Trust Assessment
feedback-mastery received a trust score of 84/100, 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, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Unjustified 'Glob' and 'Grep' permissions declared.
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 | |
| MEDIUM | Unjustified 'Glob' and 'Grep' permissions declared The skill's manifest declares 'Glob' and 'Grep' permissions, which allow listing and searching arbitrary files on the system. The skill's content describes a conversational guide and does not demonstrate any functional need for these broad filesystem access permissions. While the skill itself does not explicitly use these tools in its current markdown, their declaration increases the attack surface for potential data exfiltration or reconnaissance if the skill were to be compromised or misused by a malicious prompt. Remove 'Glob' and 'Grep' from the 'allowed-tools' declaration in the manifest. Only declare permissions that are strictly necessary for the skill's intended functionality. If 'Read' is required for companion resources, ensure its usage is limited to expected paths. | LLM | Manifest:1 | |
| 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/b9516f90ff324f51)
Powered by SkillShield