The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the bash tool to execute sentry CLI commands for data retrieval and configuration changes.
[INDIRECT_PROMPT_INJECTION]: The skill is instructed to read TELEMETRY.md from the root of a repository to obtain "query recipes" and "investigation pivots."
Ingestion points: Reads content from TELEMETRY.md in the current working directory.
Boundary markers: No specific delimiters or warnings are used when interpolating these recipes into queries.
Capability inventory: Access to Sentry API (read/write), project and team creation/modification, and alert management.
Sanitization: No explicit sanitization or validation of the file's content is performed before use.
[DYNAMIC_EXECUTION]: The skill allows for the execution of a sentry binary if it is found in the current environment's PATH, which may include binaries provided by the repository being analyzed.
Evidence: SKILL.md notes that a repository (e.g., a checkout of getsentry/sentry) can place its own sentry program first on the PATH, which the agent will then use.

sentry