The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its email-reading capabilities.
Ingestion points: The get_card_inbox_emails tool enables the agent to read incoming emails from external, untrusted sources.
Boundary markers: The instructions lack specific delimiters or directions for the agent to ignore potential instructions embedded within the retrieved email text.
Capability inventory: The agent possesses high-impact capabilities including member invitation (invite_members), role modification (set_role), email transmission (send_inbox_email), and webhook registration (create_webhook).
Sanitization: The skill does not provide instructions for sanitizing or validating external content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill instructions frequently reference the pipefy CLI to perform operations such as listing members, sending emails, and creating webhooks.
[CREDENTIALS_UNSAFE]: The tool create_service_account generates and returns sensitive credentials, specifically OAuth2 client secrets and token endpoints. The instructions prompt the agent to store these immediately, which places secrets directly into the agent's execution context.
[DATA_EXFILTRATION]: The skill allows for data to be sent to external endpoints via the send_inbox_email tool and through the configuration of external create_webhook URLs.

pipefy-members-email-webhooks