The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch live documentation and framework-specific setup guidelines from Sentry's official documentation website (docs.sentry.io) to ensure the agent uses current API patterns.
[INDIRECT_PROMPT_INJECTION]: The skill utilizes a web fetching tool to ingest external content, which establishes a potential surface for indirect prompt injection if the remote content were compromised.
Ingestion points: WebFetch call to https://docs.sentry.io/llms.txt defined in SKILL.md.
Boundary markers: None specified for the fetched content.
Capability inventory: The agent is authorized to write code, initialize SDKs, and configure monitoring settings based on the ingested data.
Sanitization: No explicit sanitization or validation of the fetched documentation content is defined within the skill instructions.

sentry