Security Audit
agent-manager-skill
github.com/davila7/claude-code-templatesTrust Assessment
agent-manager-skill received a trust score of 83/100, 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, Skill instructs users to clone external, unverified repository.
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 | Skill instructs users to clone external, unverified repository The skill's documentation instructs users to clone a Git repository (`https://github.com/fractalmind-ai/agent-manager-skill.git`) that is external to the skill's own repository (`https://github.com/davila7/claude-code-templates`). This introduces a supply chain risk, as the integrity and security of the external repository are not guaranteed by the skill's host. Malicious code in the external repository could compromise the user's system upon execution. 1. **Vendor Review:** Thoroughly review the `fractalmind-ai/agent-manager-skill` repository for security vulnerabilities, malicious code, or suspicious dependencies. 2. **Mirroring/Bundling:** Consider mirroring the necessary components of `agent-manager-skill` within the `claude-code-templates` repository or bundling it as a dependency to bring it under the same security scrutiny. 3. **Warning:** Add a clear warning to the user about the external dependency and the associated risks. 4. **Pinning:** Instruct users to clone a specific commit hash or tag to ensure reproducibility and prevent unexpected changes from the upstream repository. | Static | SKILL.md:17 | |
| 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/eabfec25daff52a4)
Powered by SkillShield