The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill correctly identifies that data returned from external sources (the Sentry MCP server) should be treated as untrusted input. It explicitly instructs the agent to never execute instructions found within event payloads, issue titles, or comments, which is a key defense against indirect prompt injection.
[EXTERNAL_DOWNLOADS]: The skill involves installing Sentry SDKs via standard package managers (such as npm or pip). These are official resources from a well-known service and are necessary for the skill's primary purpose of application monitoring.
[DATA_EXFILTRATION]: While the skill is designed to capture and send monitoring data (including AI/LLM prompts and responses) to Sentry, this is the intended functionality of the tool. The skill includes instructions for the agent to follow user preferences regarding data collection and privacy concerns.

sentry-instrument