obsidian-upgrade

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted user data to inform agent actions.
  • Ingestion points: The skill reads and audits all files within the docs/ directory and references a local 'canonical spec' file at skills/obsidian-plan-wiki/SKILL.md.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used when passing content from the wiki files to the subtask agents.
  • Capability inventory: The skill utilizes 'general-purpose' subagents and has the capability to read and modify local markdown files during the upgrade execution phase.
  • Sanitization: The skill lacks sanitization or validation logic to filter out potentially malicious instructions embedded within the markdown comments or documentation it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:48 AM