skills/bastos/skills/obsidian-daily/Gen Agent Trust Hub

obsidian-daily

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the obsidian-cli utility for note management tasks and standard system commands such as date and printf for date manipulation and text formatting. These commands are necessary for the skill's primary functionality.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by reading and searching existing note files via obsidian-cli print and obsidian-cli search-content. Malicious instructions stored in notes could be ingested into the agent context.
  • Ingestion points: Data is ingested from local files in SKILL.md using the print and search-content commands.
  • Boundary markers: No boundary markers or 'ignore' instructions are specified for note content.
  • Capability inventory: The skill allows modifying local files and changing tool configurations via the CLI.
  • Sanitization: No sanitization or content validation is performed on data retrieved from note files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 06:48 AM