Skills
skills/olivoil/skills/write-vault-section/Gen Agent Trust Hub

write-vault-section

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a CLI tool called obsidian for read and write operations. It also provides a fallback mechanism for direct filesystem access to modify markdown files in a vault.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it accepts arbitrary markdown content to be written into persistent local files.
  • Ingestion points: The content and note_path input parameters in SKILL.md are used to determine what is written and where.
  • Boundary markers: There are no instructions to use delimiters or warnings for the agent to ignore embedded instructions within the processed content.
  • Capability inventory: The skill possesses file write capabilities via the obsidian command and direct disk access.
  • Sanitization: No sanitization, escaping, or validation of the input content or file paths is described in the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 06:33 PM