Comprehensive guide for Firebase Crashlytics, including provisioning and SDK usage. Use this skill when the user needs help setting up Crashlytics, adding crash reporting, or using the Crashlytics SDK in their application.
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow mainly reads trusted first-party Maven metadata and Gradle output, but the optional `get_report` MCP step reads Crashlytics crash reports, which can carry end-user-influenced exception text and logs, though the agent does not select or force delivery of specific outsider content.
firebase/agent-skills
99954a3
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.