zentao-build
Warn
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The documentation in SKILL.md suggests using
echo $ZENTAO_TOKENto verify the environment configuration. This instruction leads to the exposure of the sensitive authentication token in the terminal output and potentially in logs.\n- [COMMAND_EXECUTION]: The skill executes thezentao-clicommand-line tool to perform operations such as listing, creating, and deleting builds.\n- [PROMPT_INJECTION]: The skill processes data from ZenTao that could contain malicious instructions (indirect prompt injection).\n - Ingestion points: Build names and details are retrieved from the server via
zentao-cli build listandzentao-cli build get.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and potential commands within the build names.\n
- Capability inventory: The skill allows the agent to modify or delete data using
zentao-cli build updateandzentao-cli build delete.\n - Sanitization: No sanitization or validation of the ingested data is performed before it is added to the agent's context.
Audit Metadata