obsidian-kanban

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill is entirely composed of markdown instructions and does not contain any executable scripts, binaries, or code files.\n- [PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by directing the agent to read and act on content from external markdown files.\n
  • Ingestion points: Data is ingested from the Obsidian kanban markdown file referenced in the workflow sections of SKILL.md.\n
  • Boundary markers: The skill does not define any delimiters or provide instructions to the agent to disregard commands embedded within the kanban file's content.\n
  • Capability inventory: The agent possesses the capability to read and modify local files through its environment tools as described in the task movement workflow.\n
  • Sanitization: There are no mechanisms described for sanitizing or validating the content extracted from the kanban files before the agent processes or displays it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 10:58 AM