skills/apitally/cli/apitally-cli/Gen Agent Trust Hub

apitally-cli

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx @apitally/cli to download and execute the vendor's command-line interface directly from the npm registry.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands for authentication, data retrieval, and querying a local DuckDB database.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from Apitally's external API, which may include untrusted content such as request headers and response bodies from monitored applications. Ingestion points: Command output from request-logs, request-details, and traces (SKILL.md, references/commands.md). Boundary markers: No specific delimiters or safety instructions are provided to the agent for handling the external NDJSON/JSON data. Capability inventory: The agent can execute shell commands via npx and perform file system operations within the ~/.apitally/ directory. Sanitization: No mechanisms for sanitizing or validating the content of the ingested API data are mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 01:47 AM