The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides methods to process user-supplied messages and external webhook payloads, which are potential vectors for indirect prompt injection attacks.
Ingestion points: Methods send_message and send_webhook (found in SKILL.md and quickstart.md) ingest string and dictionary data from untrusted sources.
Boundary markers: There are no instructions or delimiters provided to the agent to treat this data as untrusted or to ignore embedded instructions.
Capability inventory: The skill possesses network communication capabilities through the poke SDK to interact with the Poke API.
Sanitization: No sanitization or input validation logic is present in the provided reference implementations.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the poke library from the public PyPI registry. This is a standard external dependency for a vendor SDK.

poke-python