The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute various commands for diagnostics and management, including fly status, fly logs, fly machine status, fly ssh console, and curl for health endpoint testing.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which presents a surface for indirect prompt injection.
Ingestion points: The agent is instructed to read external content from application logs (fly logs), machine event statuses (fly machine status), and network responses from internal services (fly ssh console -C "curl ...").
Boundary markers: The skill includes specific instructions to exclude tokens, log bodies, configuration secrets, and user data from the diagnostic receipt to prevent data leakage.
Capability inventory: The skill has permissions to execute arbitrary fly and curl commands via the Bash tool and can read files using the Read and Grep tools.
Sanitization: There are no programmatic sanitization steps described in the skill; however, the output phase specifies a policy-based approach to filter sensitive information.

flyio-common-errors