The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data that could contain instructions intended to manipulate the agent. * Ingestion points: Fetches content from issue URLs, issue numbers, and specification file paths as part of the context gathering process. * Boundary markers: The instructions lack explicit requirements for using delimiters or 'ignore' warnings when incorporating external text into the prompt context. * Capability inventory: The skill has the capability to write local markdown files to a scratch directory and to publish issues to external trackers via network operations. * Sanitization: There are no instructions for sanitizing or filtering the fetched external content before the agent evaluates it to generate ticket descriptions.
[NO_CODE]: The skill is comprised entirely of markdown instructions and does not include any scripts, binaries, or executable code, which reduces the surface area for direct malicious execution.

to-tickets