embedded-project-loop

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill specifies the execution of a local script, python3 scripts/run_arduino_evals.py, to verify the integrity of project artifacts and state files.\n- [PROMPT_INJECTION]: The skill processes project-specific data from the .arduino/ directory, creating a surface for indirect prompt injection.\n
  • Ingestion points: The agent is instructed to read goal.md, next-todo.md, and other state files located in the .arduino/ folder in SKILL.md.\n
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the state files.\n
  • Capability inventory: The skill facilitates writing to a ledger and executing a local evaluation script as defined in SKILL.md.\n
  • Sanitization: No explicit sanitization or validation of the content within the state files is described, though the skill warns users to exclude sensitive data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 09:48 PM
Security Audit — agent-trust-hub — embedded-project-loop