The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs network requests to api.fxtwitter.com to retrieve tweet data in JSON format. This involves communicating with a third-party service that is not part of the standard whitelisted domains for data exfiltration analysis.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted content from the internet.
Ingestion points: Data enters the agent's context through the WebFetch call to the fxtwitter API, specifically the tweet.text field which contains arbitrary user-generated content from X/Twitter.
Boundary markers: The instructions do not define clear delimiters (e.g., XML tags or triple quotes) or provide the agent with a 'security preamble' to ignore instructions embedded within the fetched tweet text.
Capability inventory: The skill uses WebFetch for reading data. It does not include tools for file system modification, subprocess execution, or shell access.
Sanitization: The skill does not implement any validation, escaping, or filtering of the fetched JSON data before presenting it to the agent or the user.

fetch-tweet