The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard git and grep commands for gathering incident-related context, such as commit history, file diffs, and error patterns in source code.
[SAFE]: All operations are performed locally within the project directory. The skill does not initiate network connections, download external scripts, or attempt to exfiltrate sensitive information.
[SAFE]: The skill ingests data from git history and source files (Ingestion points: SKILL.md), uses markdown for boundary markers, has access to tools including Bash and Read (Capability inventory: SKILL.md), and performs no automated sanitization. However, this ingestion is used for reporting purposes rather than execution, making the risk profile safe for its intended primary use case.

incident-report