signoz-cli
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@jcit/signozpackage from the npm registry. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
signozCLI, as well as system tools likesecurity(macOS) andsecret-tool(Linux) for credential management. - [DATA_EXFILTRATION]: The skill handles sensitive SigNoz API tokens (
SIGNOZ_TOKEN) and interacts with user-defined SigNoz API endpoints to retrieve traces, logs, and metrics. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingest and processes untrusted data from SigNoz (logs and traces) which could contain malicious instructions.
- Ingestion points: Data returned from
signoz querycommands (SKILL.md). - Boundary markers: No specific delimiters or instructions are provided to the agent to ignore embedded commands in the query results.
- Capability inventory: The agent has the capability to execute shell commands (
signoz) and read/write local files (-fflag). - Sanitization: No sanitization or validation of the observability data is mentioned before processing.
Audit Metadata