The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to perform network operations against Sentry's API endpoints (*.sentry.io). These actions are necessary for the skill's function and target the vendor's own well-known infrastructure.
[DYNAMIC_EXECUTION]: The skill instructs the agent to generate and run short Python one-liners (python3 -c) to parse and filter JSON data. While these are simple scripts derived from static templates, they involve string interpolation of user or API data into an executable context.
[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes data from external API endpoints (e.g., member lists, integration details) that could contain attacker-controlled strings. This creates a potential surface for indirect injection if that data is processed without sufficient validation.
Ingestion points: Data is ingested from Sentry API endpoints such as /members/, /teams/, and /integrations/ (SKILL.md).
Boundary markers: None; the instructions do not define delimiters or specific safety warnings for the agent when handling this external JSON content.
Capability inventory: The skill has the ability to read from and write to Sentry's workflow engine using curl, and to execute local code via python3.
Sanitization: There are no explicit instructions for the agent to sanitize or escape the API-provided strings before they are utilized in scripts or reported back to the user.

sentry-create-alert