The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes git log and git blame to analyze repository history for developer attribution.
[EXTERNAL_DOWNLOADS]: The configuration in .mcp.json specifies the use of npx to download and execute firebase-tools, which is an official package from a well-known service provider.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external crash data from Firebase to generate reports. This input is processed without explicit sanitization or delimiters, creating a potential attack surface for indirect prompt injection.
Ingestion points: External crash data is fetched via the Firebase MCP server tool in commands/crash-report.md.
Boundary markers: None identified in the instructions.
Capability inventory: The skill has the ability to read codebase files, perform git operations, and write output files.
Sanitization: No input validation or sanitization routines are specified for the external crash logs.

crashlytics