digs

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes mkdir and grep for managing and searching local research files within a dedicated workspace directory. These operations are limited to the skill's data folder.
  • [EXTERNAL_DOWNLOADS]: A reference to the author's official GitHub repository is provided for manual updates, which is a standard practice and originates from the identified author's infrastructure.
  • [PROMPT_INJECTION]: The skill processes user-provided external links. Risk is addressed by instructing the agent to synthesize findings rather than ingesting raw data as instructions. Ingestion point: User-provided links. Boundary markers: Absent. Capability inventory: File system operations (mkdir, mv, write), grep. Sanitization: Instruction to synthesise findings into dated entries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 10:46 AM
Security Audit — agent-trust-hub — digs