impl-do
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill directs subagents to execute various development commands, including linters (eslint, ruff, golangci-lint), type checkers (tsc, mypy), build scripts, and test suites to verify task completion. It also uses Git commands for task commits.
- [PROMPT_INJECTION]: The skill features an indirect prompt injection surface by ingesting and acting upon instructions found in project plan files and communication files. Ingestion points: plan.json, plan.md, and the mail/ directory. Boundary markers: Not specified in the instructions. Capability inventory: Execution of project commands (lint, test, build) and file system/Git operations. Sanitization: No sanitization of external content is performed.
- [NO_CODE]: The skill consists solely of Markdown instruction files and does not contain any executable scripts, binaries, or configuration files that run code.
Audit Metadata