workflow-test-spec-update
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a workflow that ingests untrusted user input and passes it as context to a sequence of automated commands.
- Ingestion points: The entire user prompt is used as the execution context for the
test-spec-updateworkflow. - Boundary markers: There are no delimiters (like triple quotes or XML tags) or system instructions provided to the agent to treat the user input as data rather than instructions.
- Capability inventory: The workflow executes steps including
/testand/integration-test, which typically involve shell command execution and code evaluation. - Sanitization: The skill does not describe any validation or sanitization of the user prompt before passing it to the workflow tools.
Audit Metadata