obsidian-vault-management
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes Python scripts that traverse and parse all markdown notes within a vault to generate tag and link reports. This functionality creates a surface for indirect prompt injection where maliciously crafted notes could influence the agent's behavior during analysis.\n
- Ingestion points:
scripts/tag-overview.pyandscripts/find-orphan-notes.pyingest content from all.mdfiles in the vault.\n - Boundary markers: The scripts do not implement specific delimiters or instructions to ignore embedded commands within the processed markdown content.\n
- Capability inventory: The skill includes scripts with file system read and write capabilities (
Path.write_text,md_file.read_text).\n - Sanitization:
yaml.safe_load()is correctly utilized inscripts/tag-overview.pyto parse frontmatter, providing protection against YAML-based injection attacks.\n- [COMMAND_EXECUTION]: The skill provides standalone Python scripts designed to be executed via the command line for vault management tasks, representing a standard interface for local command execution.
Audit Metadata