more-with-less-agent-factory
Explain or summarize Baruch Sadogursky's delivered JRush 2026 talk “More With Less,” including its triple policy enforcement, skills/scripts/classifiers split, Jev example, diminishing-returns judge, Herdr roles, and model economics. Use for questions about this specific talk, its demos, or its cited resources.
72
91%
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
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The skill instructs the agent to read GitHub issues (such as coding-policy issue #632) and other external repository content where outsiders can submit free text.
- Repository
- jbaruch/shownotes
- Commit
f8c9b77
- Audited
- Security analysis
Is this your skill?
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.