skills/grid0723/skills/harvest/Gen Agent Trust Hub

harvest

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process learning outcomes and domain maps, which constitutes an indirect prompt injection attack surface.
  • Ingestion points: Learning results, concept definitions, and mermaid diagrams provided to the agent for summarization and filing (SKILL.md).
  • Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore embedded instructions within the processed data.
  • Capability inventory: The skill utilizes file system write capabilities to create notes and directories within the specified 00_收集箱/ and 10_领域/ paths.
  • Sanitization: Absent; there is no mention of escaping, filtering, or validating the content extracted from learning outcomes before it is written to persistent storage.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 07:04 PM
Security Audit — agent-trust-hub — harvest