what-would-lenny-do
Answers product strategy, growth, pricing, hiring, and leadership questions using Lenny Rachitsky's archive. ONLY use this skill if the `lennysdata` MCP server is connected and its tools (search_content, read_content, etc.) are available. If the lennysdata MCP is not connected, do NOT use this skill — respond using your own knowledge instead.
67
84%
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.md explicitly instructs the agent to query and read external archive content via lennysdata tools (e.g., `lennysdata:search_content`, `lennysdata:read_content`, `lennysdata:list_content`), which fetches public third‑party newsletter/podcast material that the agent must interpret and use to drive recommendations — exposing it to untrusted third‑party text that could contain instructive payloads.
- Repository
amplitude/builder-skills
- Revision
51838c2
- 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.