The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data (crash logs, stack traces, and user reviews) to generate triage reports.
Ingestion points: Processed data enters via user-provided crash reports and review text in the triage and debugging sections.
Boundary markers: The provided templates do not include explicit delimiters or instructions to ignore embedded commands within the crash data.
Capability inventory: The skill uses standard text processing to generate reports but relies on the underlying agent's capabilities for any subsequent actions (e.g., file system navigation or shell execution mentioned in the manual steps).
Sanitization: There is no explicit sanitization or filtering of the content within the crash reports before they are interpolated into the 'Stability Report' output format.
[EXTERNAL_DOWNLOADS]: The skill references the com.google.firebase:firebase-crashlytics dependency. This is an official package from a well-known service provider and is documented neutrally.
[SAFE]: The skill provides standard, non-malicious code snippets for initializing the Firebase SDK in iOS (Swift) and Android (Kotlin) applications.

crash-analytics