personal-knowledge

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of instructional text and configuration files. It does not include Python, JavaScript, or shell scripts.\n- [SAFE]: No security issues were detected. The skill performs standard note-taking operations (search, summarize, save) within its intended scope and uses standard YAML configuration.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external note content retrieved via search, which constitutes a theoretical data ingestion surface. However, the risk is negligible as the skill lacks high-privilege capabilities such as shell access or filesystem modification.\n
  • Ingestion points: Blinko search results (SKILL.md).\n
  • Boundary markers: None specified in the instructions.\n
  • Capability inventory: Tools to search and save notes to the Blinko service.\n
  • Sanitization: None mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 05:49 PM
Security Audit — agent-trust-hub — personal-knowledge