skills/zerodeploy-dev/skills/status/Gen Agent Trust Hub

status

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the zerodeploy CLI to list deployments and retrieve site statistics. These actions are standard for managing and monitoring the vendor's own service.
  • [DATA_EXPOSURE]: The skill reads the zerodeploy.json configuration file to extract organization and site slugs. This access is restricted to public-facing project identifiers and does not include sensitive system files or private credentials.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes and summarizes data from the project configuration and tool outputs. 1. Ingestion points: Data enters the context via the zerodeploy.json file and the output of the zerodeploy command. 2. Boundary markers: The instructions do not specify the use of delimiters or 'ignore' markers for the ingested data. 3. Capability inventory: The agent's capabilities are restricted to executing the zerodeploy command-line utility. 4. Sanitization: No explicit validation or filtering of the ingested data is performed before it is summarized for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 06:00 PM