Trust Assessment
beeper-api-cli received a trust score of 14/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 2 critical, 1 high, 2 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Sensitive environment variable access: $HOME, Potential Beeper Token Exfiltration via Malicious BEEPER_API_URL.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | 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 | skills/nerveband/beeper-api-cli/SKILL.md:280 | |
| CRITICAL | 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 | skills/nerveband/beeper-api-cli/SKILL.md:356 | |
| HIGH | Potential Beeper Token Exfiltration via Malicious BEEPER_API_URL The `beeper.sh` script sends the `BEEPER_TOKEN` to the URL specified by the `BEEPER_API_URL` environment variable during its API readiness check. While the default is localhost, a compromised LLM or malicious user could set `BEEPER_API_URL` to an external, untrusted server. This would lead to the exfiltration of the `BEEPER_TOKEN` to an attacker-controlled endpoint. The script does not validate the `BEEPER_API_URL` to ensure it points to a trusted Beeper Desktop instance or a safe IP range. Implement validation for `BEEPER_API_URL` to restrict it to known safe patterns (e.g., localhost, private IP ranges, or require explicit user confirmation for external IPs). Alternatively, ensure the LLM is strictly sandboxed from setting arbitrary environment variables or that `BEEPER_API_URL` is always controlled by a trusted system component. | LLM | beeper.sh:28 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nerveband/beeper-api-cli/SKILL.md:369 | |
| MEDIUM | Hardcoded Absolute Path to Beeper CLI Binary The `beeper.sh` script uses a hardcoded absolute path (`/Users/ashrafali/clawd/skills/beeper-api-cli/beeper`) for the `BEEPER_CLI` binary. This introduces a supply chain risk:
1. **Portability**: The skill will likely fail on systems where this exact path does not exist.
2. **Tampering**: If a malicious actor gains control over this specific path on the host system, they could replace the legitimate `beeper` binary with a malicious executable, leading to arbitrary code execution when the skill is invoked. This relies on the integrity of a specific, non-relative file path. Modify the script to use a path relative to its own location (e.g., `BEEPER_CLI="$(dirname "$0")"/beeper`) or ensure the binary is installed in a standard, secure system location and resolved via `PATH`. | LLM | beeper.sh:5 |
Scan History
Embed Code
[](https://skillshield.io/report/cddf9e22d2749a17)
Powered by SkillShield