The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes inquiries from an external API, creating a potential surface for indirect instructions to be processed by the agent.
Ingestion points: Data is ingested from the Persona API inquiry endpoint in the Python implementation within SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the ingested API data.
Capability inventory: The skill is configured with Read, Write, Edit, and Bash tool capabilities.
Sanitization: The implementation prints the API response attributes directly without validation or filtering.
[DATA_EXFILTRATION]: The skill performs network operations to an external identity verification service.
Network operations: The skill fetches data from withpersona.com. This is a well-known service for identity verification, and the connection is used for its primary stated purpose.
Credential management: The skill follows security best practices by accessing the Persona API key via the PERSONA_API_KEY environment variable.

persona-upgrade-migration