The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the npx @useclawlink/cli command to interact with Sentry. It performs various actions including fetching alerts, retrieving project information, and executing issue-related tasks.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to run commands via npx, which downloads the @useclawlink/cli package from the NPM registry at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could potentially contain malicious instructions.
Ingestion points: Untrusted data enters the agent context through actions such as sentry_fetch_issue_event_by_id, sentry_fetch_alerts, and sentry_access_project_information, which read content from Sentry issues and organization alerts.
Boundary markers: The skill documentation does not define specific delimiters or instructions for the agent to ignore embedded commands within the Sentry data.
Capability inventory: The agent has the capability to execute shell commands via the ClawLink CLI, which includes write operations like sentry_add_organization_member_via_email and sentry_add_a_symbol_source_to_a_project.
Sanitization: There is no evidence of specific sanitization or filtering applied to the data retrieved from Sentry before it is processed by the agent.

sentry