Trust Assessment
prometheus 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 2 findings: 0 critical, 1 high, 0 medium, and 1 low severity. Key findings include Node lockfile missing, Potential credential exfiltration via manipulated PROMETHEUS_URL.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential credential exfiltration via manipulated PROMETHEUS_URL The skill uses environment variables `PROMETHEUS_URL`, `PROMETHEUS_USER`, and `PROMETHEUS_PASSWORD` for connecting to a Prometheus server. The `PROMETHEUS_USER` and `PROMETHEUS_PASSWORD` are base64 encoded and sent as an HTTP Basic Auth header to the `PROMETHEUS_URL`. If an attacker can manipulate the `PROMETHEUS_URL` environment variable (e.g., by instructing the LLM to set it to an attacker-controlled server before invoking the skill), any provided credentials will be sent to the malicious URL, leading to credential exfiltration. Implement strict validation or allowlisting for `PROMETHEUS_URL` if it can be influenced by untrusted input. If the LLM is responsible for setting environment variables, ensure it is explicitly instructed *not* to set `PROMETHEUS_URL` from untrusted user input. Consider using a secure credential store or a more robust authentication mechanism if possible, rather than relying solely on environment variables for sensitive data. | LLM | scripts/common.js:44 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/akellacom/prometheus/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/73e8e1a0c08e46f4)
Powered by SkillShield