The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content retrieved from X/Twitter posts, which creates a surface for indirect prompt injection attacks.
Ingestion points: The skill fetches the tweet.text and tweet.quote fields from the api.fxtwitter.com response into the agent's context for summarization and translation.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the fetched content as untrusted data or to ignore embedded commands.
Capability inventory: The skill uses WebFetch to perform network operations and retrieve data from external URLs.
Sanitization: The skill lacks sanitization, filtering, or validation steps to ensure the fetched tweet text does not contain malicious instructions.
[COMMAND_EXECUTION]: The skill uses the WebFetch tool to execute network requests to the api.fxtwitter.com service to retrieve JSON data.

my-fetch-tweet