skills/canhassancode/skills/observe/Gen Agent Trust Hub

observe

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Uses standard shell commands (date, echo) to resolve the vault path and generate timestamps for log entries. These commands are localized and used only for formatting.
  • [DATA_EXPOSURE]: Interacts with a local directory (defaulting to ~/Obsidian) to append user-provided observations. The skill instructions explicitly prohibit writing sensitive data such as credentials, tokens, or PII into the log file, providing a clear security boundary for the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 09:26 AM