The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill contains GitHub Actions templates that install the Sentry CLI by downloading and piping a shell script from Sentry's official domain (sentry.io) to bash.
[EXTERNAL_DOWNLOADS]: The skill uses the npx @sentry/wizard@latest command to perform automated project setup, fetching the tool from the official NPM registry.
[COMMAND_EXECUTION]: Local environment detection relies on shell utilities like find and grep to locate project files and existing configurations.
[COMMAND_EXECUTION]: The provided CI workflow templates include sudo xcode-select commands to configure the macOS build environment on GitHub Actions runners.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files which serves as an ingestion point for external data into the agent's context.
Ingestion points: Project files including Package.swift, Package.resolved, and project.pbxproj are read during the detection phase in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded instructions within these files.
Capability inventory: The skill has access to shell execution, network downloads, and remote script execution.
Sanitization: The file contents are not sanitized or validated for malicious prompts before being processed by the agent.

sentry-snapshots-cocoa