NYC
skills/smithery/ai/log-to-obsidian/Gen Agent Trust Hub

log-to-obsidian

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Prompt Injection (LOW): The skill exhibits a surface for indirect prompt injection by design.
  • Ingestion points: The skill explicitly reads and summarizes external 'session' logs and 'git history' (SKILL.md, Step 2).
  • Boundary markers: No delimiters or safety instructions are defined to prevent the agent from following commands that might be embedded within the git logs or session data.
  • Capability inventory: The skill is designed to write and append content to markdown files within the user's local directory (~/Documents/nls).
  • Sanitization: There is no logic provided to sanitize or escape the content retrieved from logs before processing it into the final note.
  • Data Exposure & Exfiltration (SAFE): While the skill accesses local document paths, there are no network functions or commands that would facilitate external data transfer.
  • Remote Code Execution (SAFE): No external dependencies or script execution patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:49 PM