The Agent Skills Directory

[SAFE]: No security issues detected. The skill instructions and associated scripts are focused on organizational workflows and project lifecycle management.
[COMMAND_EXECUTION]: The skill includes a local Python script, scripts/scan_changes.py, which manages project change folders on the filesystem. The script's actions are limited to scanning directory structures for task completion markers and moving completed folders to an archive directory. It does not perform any network operations, access sensitive system files, or execute external shell commands.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for processing project-related data and user-provided notes to facilitate documentation generation. 1. Ingestion points: The agent reads content from local project files and handles user-provided utterances for feature extraction. 2. Boundary markers: The skill relies on structured project conventions defined in its reference documents but does not utilize technical delimiters to isolate processed data from instructions. 3. Capability inventory: Capabilities are limited to creating and moving project-related markdown files on the local disk; no network or shell execution capabilities are present. 4. Sanitization: No specific data sanitization routines are included in the provided logic.

project-operations