skills/davidlee/doctrine/next/Gen Agent Trust Hub

next

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates handoffs between agent contexts, which constitutes a multi-step prompt chain vulnerable to indirect injection.
  • Ingestion points: Instructs the agent to read and summarize files such as design.md, plan.toml, and active phase sheets.
  • Boundary markers: The skill does not provide instructions to wrap summarized content in protective delimiters or to ignore embedded commands within the artifacts.
  • Capability inventory: The skill's primary function is text generation; it does not request or use tools for shell execution, file writing, or network access.
  • Sanitization: There is no requirement for the agent to sanitize or validate the content of the project files before including it in the handoff prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 11:56 PM
Security Audit — agent-trust-hub — next