The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from the Hashnode API, such as post bodies, comments, or user bios, which could potentially contain instructions intended to influence the agent's behavior.
Ingestion points: The skill fetches data from the https://gql-beta.hashnode.com endpoint, including fields such as contentMarkdown, bio, and faq.
Boundary markers: There are no instructions or delimiters provided to isolate untrusted content from the agent's core instructions.
Capability inventory: The skill allows the agent to perform both read and write operations (mutations) on publications via the GraphQL API using the user's Personal Access Token.
Sanitization: The skill does not mention any mechanisms for sanitizing or escaping the data retrieved from the API before it is processed by the agent.
[COMMAND_EXECUTION]: The skill provides curl command templates for interacting with the Hashnode API, which is a standard method for API communication.
The commands utilize the $HASHNODE_PAT environment variable for authentication, which is an industry best practice for secure secret management.
The target endpoint https://gql-beta.hashnode.com is the official resource provided by the vendor for GraphQL operations.
The skill also provides a curl example for binary file uploads to a presigned URL for image management, which is a routine functional capability for a publishing API.

gql-api