team-implement
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local shell scripts (
discover-topic.shandplan-id.sh) to perform environment-specific path resolution and identifier creation. - [COMMAND_EXECUTION]: It performs operations using
gitto manage linked worktrees andgrepto verify implementation details, which are standard actions for development-focused agents. - [INDIRECT_PROMPT_INJECTION]: The skill's workflow depends on reading potentially untrusted data from plan files (
1-task.md,8-plan.md). It mitigates the risk of indirect injection by instructing the agent to ignore any 'embedded imperatives' found within those files.
Audit Metadata