executor
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute various shell commands for code validation and database management. Specific evidence includes the instructions to use 'npx tsc --noEmit' for TypeScript, 'mypy' and 'ruff check' for Python, 'pytest' for testing, and 'alembic revision' for SQL migrations as detailed in the SOP steps of SKILL.md.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it autonomously implements instructions from an external checklist. 1. Ingestion points: Task descriptions provided via the planner-generated checklist (SKILL.md). 2. Boundary markers: Absent; there are no specific markers to delineate task content from instructions. 3. Capability inventory: Significant file system access (read/write) and shell command execution (SKILL.md). 4. Sanitization: Not implemented; the agent is instructed to implement tasks 'precisely' without descriptive validation of the task source.
Audit Metadata