write-flow-guide
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Python CLI tool (
scripts/flow-guide) included within the skill package to manage artifacts and render HTML reports. These operations are performed on local files and do not involve arbitrary shell command execution. - [DATA_EXFILTRATION]: The skill includes a
servecommand that initiates a local HTTP server bound strictly to the loopback interface (127.0.0.1). Access is restricted to the local machine for manual human review of the generated guides. No external network connections or exfiltration patterns were detected. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process project documentation (e.g., requirements and design files) to generate test cases. While this represents a data ingestion surface, the skill utilizes structured JSON and renders HTML guide templates with standard character escaping, mitigating risks from payloads embedded in the source documentation.
- [REMOTE_CODE_EXECUTION]: The skill relies entirely on code distributed within its own package. It does not download external scripts or execute code from remote sources.
Audit Metadata