Running audience Q&A at an all-hands, AMA, webinar, launch, sprint review or talk, or turning a session's questions into a FAQ: collect, moderate, answer and follow up every question. AskOne by default.
92%
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 integrates with AskOne via MCP to collect and moderate audience-submitted questions from live Q&A sessions, presenting untrusted participant text directly to the agent runtime.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill instructs configuring an MCP server via a remote URL (`https://askone.org/api/mcp`) and running an external npm package (`npx skills add phuryn/askone`) at runtime, constituting an unverifiable runtime external dependency from an unofficial third-party source.
phuryn/pm-skills
9af7bfd
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.