synapse-reinst

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to re-inject initial system instructions into the agent's context after a reset. It instructs the agent to "Follow the instructions as if they were just sent to you" to restore its identity and role. While this follows a prompt injection pattern, it is the intended and documented purpose of the recovery tool and operates using local configuration templates.
  • [COMMAND_EXECUTION]: The skill provides a Python script (scripts/reinst.py) used to retrieve configuration data. The script performs legitimate local operations such as reading environment variables, checking process IDs (PPID), and parsing local JSON/Markdown files in the user's directory to reconstruct the agent's state.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 04:25 PM