The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires connecting to an external MCP server endpoint at https://rube.app/mcp to access the Sentry toolkit functionality.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from Sentry environments that can be influenced by external actors.
Ingestion points: Untrusted data such as stack traces, error messages, and issue tags are retrieved via tools like SENTRY_LIST_AN_ISSUES_EVENTS and SENTRY_RETRIEVE_AN_ISSUE_EVENT as described in SKILL.md.
Boundary markers: The instructions do not include delimiters or specific guidance to treat external Sentry data as potentially untrusted input.
Capability inventory: The skill possesses capabilities to modify Sentry configurations, including SENTRY_CREATE_PROJECT_RULE_FOR_ALERTS and SENTRY_CREATE_RELEASE_FOR_ORGANIZATION (found in SKILL.md).
Sanitization: There are no instructions for sanitizing or escaping the data retrieved from Sentry before it is used in subsequent agent steps or workflows.

sentry-automation