The Agent Skills Directory

[SAFE]: The skill is a standard implementation for interacting with Sentry's API via the Rube MCP (Composio) toolkit. It uses documented tools for managing issues, events, alerts, and releases.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection, which is typical for observability tools that process external error data.
Ingestion points: Untrusted data enters the agent context through tools like SENTRY_LIST_AN_ISSUES_EVENTS and SENTRY_RETRIEVE_AN_ISSUE_EVENT which fetch stack traces, error messages, and issue logs from Sentry.
Boundary markers: The instructions do not explicitly mandate the use of delimiters or "ignore embedded instructions" warnings when processing error content.
Capability inventory: The skill possesses significant write capabilities, including SENTRY_CREATE_PROJECT_RULE_FOR_ALERTS, SENTRY_UPDATE_A_MONITOR, and SENTRY_CREATE_RELEASE_FOR_ORGANIZATION.
Sanitization: There are no instructions for sanitizing or escaping the content retrieved from Sentry before it is processed by the agent.

sentry-automation