The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local setup and analysis commands using the Bash tool. Specifically, it installs the current directory as an editable Python package (pip install -e .) and runs a local scanning script (apex_agent/apex_scan.py). These actions are performed to generate automated health snapshots of the codebase.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading git log and git diff outputs, as well as the contents of source files. This data is used as context for the agent's code review. While this constitutes an attack surface for indirect prompt injection, it is the primary and intended function of an automated review tool.
[DATA_EXFILTRATION]: The skill writes a scan report to /tmp/apex-scan.json and may use the WebFetch tool to retrieve external data. There are no patterns indicating automated exfiltration of sensitive user data; network tools are used in accordance with the skill's purpose for broad engineering reviews.

apex-review