skills/rakaadi/agent-kit/execute-plan/Gen Agent Trust Hub

execute-plan

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes implementation plans and repository instructions which serve as inputs for the agent's actions and subagent dispatches. \n
  • Ingestion points: External implementation plans (Markdown/HTML), repository-specific instructions, and user-provided runtime overrides defined in SKILL.md. \n
  • Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are mentioned for the ingestion of external plan content. \n
  • Capability inventory: Performs repository edits, file creation, execution of verification commands, and subagent dispatch. \n
  • Sanitization: The skill relies on manual gates (Program Design Gate, Architectural Review) rather than automated sanitization of ingested plan data. \n- [COMMAND_EXECUTION]: The skill is instructed to 'Run task-level verification' and 'final verification', which involves the execution of shell commands or test suites defined within the repository or the plan content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 06:50 AM
Security Audit — agent-trust-hub — execute-plan