The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches external, user-generated content from Stack Overflow via the Stack Exchange API, which could potentially contain malicious instructions intended for the processing agent.
Ingestion points: Content is fetched in the form of question and answer bodies as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or isolation protocols when the agent processes the retrieved content.
Capability inventory: The skill utilizes curl for network read operations to retrieve API data.
Sanitization: There are no instructions provided for sanitizing, escaping, or filtering the retrieved user content before it is processed by the agent.
[SAFE]: The skill performs network requests to api.stackexchange.com using curl. This is the official API domain for Stack Exchange, a well-known service, and the operations are limited to fetching data without hardcoded credentials.

readable-stackoverflow