plan-execution-v3
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands for code quality verification including formatting, linting, type-checking, and compilation based on definitions found in local task files (
tasks/T-*.md). - [PROMPT_INJECTION]: The skill ingests data from external markdown files to guide implementation logic and command execution, which presents a surface for indirect prompt injection. 1. Ingestion points:
tasks/T-*.md,research/RT-*.md, andevidence/EVD-*.md(SKILL.md, Execution Steps 1 and 2). 2. Boundary markers: Absent. 3. Capability inventory: Execution of arbitrary shell commands for project building and testing (SKILL.md, Execution Step 6). 4. Sanitization: Absent.
Audit Metadata