Trust Assessment
team-communication-protocols received a trust score of 49/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 1 critical, 1 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Potential Local File Read for Team Configuration.
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 11, 2026 (commit 5d65aa10). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | plugins/agent-teams/skills/team-communication-protocols/SKILL.md:129 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | plugins/agent-teams/skills/team-communication-protocols/SKILL.md:129 | |
| MEDIUM | Potential Local File Read for Team Configuration The skill explicitly instructs agents to read a local file located at `~/.claude/teams/{team-name}/config.json` to discover team members. While the provided example structure of `config.json` does not show explicit credentials, it contains internal `agentId`s and `agentType`s. This instruction implies that agents are expected to have filesystem access to this specific path. If an agent is compromised or misconfigured, it could read this file and potentially exfiltrate its contents, leading to information disclosure about the team's internal structure and identifiers. This constitutes a data exfiltration risk if the agent's environment is not properly sandboxed or if the file contains sensitive data. 1. Ensure that the agent's execution environment strictly controls filesystem access, allowing read-only access only to necessary paths and preventing unauthorized exfiltration channels. 2. Review the contents of `config.json` to ensure no sensitive information (e.g., API keys, secrets) is stored there. 3. Consider providing team member information to agents through secure, in-memory mechanisms or dedicated APIs rather than requiring direct filesystem access. 4. If filesystem access is deemed necessary, implement strict access control lists (ACLs) or sandboxing to limit what files can be read and by whom. | LLM | SKILL.md:100 |
Scan History
Embed Code
[](https://skillshield.io/report/774ea180ae64fd6b)
Powered by SkillShield