rpe-grafana
Analysis
This skill appears to do what it says—read Grafana dashboards and panel values—but it needs Grafana credentials, so it should be configured with a read-only account.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
const queryRes = await grafanaFetch(url, user, password, "/api/ds/query", { method: "POST", body: JSON.stringify({ queries, from, to }) });The tool can ask Grafana to execute stored panel queries through the datasource query API. It is scoped to existing dashboard panels rather than arbitrary user-supplied query text.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
user: pc.user || process.env.GRAFANA_USER || "admin", password: pc.password || process.env.GRAFANA_PASSWORD || "", ... Authorization: basicAuth(user, password)
The skill uses configured or environment Grafana credentials and sends them in an Authorization header for Grafana API requests.
