clinkding

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's instructions and commands are consistent with the purpose of bookmark management and do not exhibit malicious behavior.
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions targeting the official GitHub repository for the clinkding project via Homebrew and Go.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from bookmark titles and descriptions, creating a surface for indirect prompt injection. Ingestion points: Bookmark metadata retrieved from Linkding and external summaries fetched via the summarize skill. Boundary markers: Absent. Capability inventory: clinkding CLI operations (save, update, delete). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:25 AM