flow-next-plan-review
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
evalto execute shell commands produced by the bundledflowctlscript, which is used to initialize session-specific environment variables (WandT) within the agent's shell environment. - [DATA_EXFILTRATION]: Project source files and specification documents are transmitted to external analysis services, including RepoPrompt, OpenAI, and GitHub Copilot, for automated review processing.
- [PROMPT_INJECTION]: The skill's instructions in
SKILL.mdandworkflow.mdexplicitly command the agent to bypass user confirmation and avoidAskUserQuestioncalls during the fix-and-review loop. This behavior, coupled with the ingestion of external reviewer feedback and project code (ingestion points), establishes an indirect prompt injection surface. The skill utilizes boundary markers like<file_contents>and<verdict>tags to delimit content, and its capabilities include executing theflowctltool for filesystem and network access. Sanitization is performed via regex parsing of the final verdict.
Audit Metadata