soia-pkm-organize

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill reads and processes user-controlled Markdown files from an Obsidian vault to determine categorization via LLM analysis.
  • Ingestion points: scripts/rebuild_moc.py reads Markdown files (*.md) within the vault.
  • Boundary markers: No explicit boundary markers or instructions to the LLM to ignore embedded commands are present in the parsing logic.
  • Capability inventory: The skill has the capability to write and delete files (specifically within the _MOC directory) in the local file system.
  • Sanitization: No specific sanitization is applied to the content of the Markdown files before processing.
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/rebuild_moc.py to perform file operations within the user's vault. The script includes destructive operations such as shutil.rmtree to clear the _MOC directory during the reorganization process.
  • [EXTERNAL_DOWNLOADS]: The documentation includes an installation command npx skills add soia-team/soia-open-skills. This targets a vendor-owned repository and is part of the standard installation workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 03:07 AM
Security Audit — agent-trust-hub — soia-pkm-organize