The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted content from the OpenServ Ideaboard API, which is a vector for indirect prompt injection.
Ingestion points: GET /ideas and GET /ideas/:id endpoints fetch title, description, and comments (as documented in reference.md).
Boundary markers: The instructions do not define any delimiters or ignore-instructions for the processed external data.
Capability inventory: The agent has the capability to perform POST requests to pick up and ship ideas based on the ingested instructions.
Sanitization: No sanitization or validation mechanisms are described for handling the API-provided strings.
[CREDENTIALS_UNSAFE]: The examples/get-api-key.ts script logs a generated WALLET_PRIVATE_KEY to the console. This practice can lead to accidental credential exposure if the agent's output is recorded in logs.
[EXTERNAL_DOWNLOADS]: The documentation suggests fetching and updating skills from the openserv-labs/skills repository via the npx skills command.

openserv-ideaboard-api