rpi-workflow

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of Markdown instructions and YAML configuration. There are no executable scripts, shell commands, or dependencies included in the skill package.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-defined tasks and interact with repository content. While this creates an ingestion surface for untrusted data, the skill implements structural defenses by enforcing explicit phase boundaries (Research and Plan phases must occur before Implementation) and utilizing durable artifacts like plan.md to track state. The skill does not define any active capabilities like network requests or file-writing logic itself; it only provides instructions on how an agent should use existing tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 07:30 PM