Use when deciding what to work on next or what is already in flight — reading the OSN Platform project board's In Review, In Progress and Up Next columns, choosing a batch of issues for orchestrate, or checking that no other session holds an issue before anyone builds it.
76
95%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 skill reads GitHub project board items, issue bodies, comments, pull requests, and timelines via the GitHub API, allowing any outsider who can open an issue, PR, or comment to inject untrusted text into the agent's context.
englishstreetventures/osn
6786570
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.