The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified during the analysis of the skill instructions, scripts, or metadata.
[COMMAND_EXECUTION]: The skill includes two local shell scripts (validators/pre-check.sh and validators/post-check.sh) designed for environment validation and constraint verification. These scripts use standard utilities like grep and echo to verify that the output remains within the defined triage boundaries and does not contain prohibited synthesis markers.
[DATA_EXPOSURE]: Data access is strictly scoped to the user's Obsidian Inbox/ directory. The skill enforces a 'read-only' posture for analysis, only proposing changes (moving or tagging files) for the user to confirm manually, which prevents unauthorized data modification or exposure.

inbox-triage