The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads the ticket body, which is a GitHub issue (it carries `Blocked by:` issue references and the `ready-for-agent` label), and the skill itself treats that body as untrusted, so an outsider can write into a GitHub issue the workflow consumes without the agent selecting a specific item.
agranado2k/ai-report-platform
caeb0da
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.