skills/azhi-ss/ljg-skills/ljg-think/Gen Agent Trust Hub

ljg-think

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the system 'date' command to generate formatted timestamps for file naming and document metadata, representing a standard and benign use of local utilities.
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface by processing untrusted user input and writing it to the file system. 1. Ingestion point: User-supplied 'viewpoints' or 'phenomena' in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Executes 'date' and performs file write operations to '~/Documents/notes/'. 4. Sanitization: Absent. The resulting output is a static .org file, which poses no execution risk to the system.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 07:13 PM