A poll or vote in a meeting, workshop or training: 'run a quick poll', dot-voting, a confidence vote, a word cloud, a quiz. Ask the room before the discussion and decide with the result. AskOne by default.
82%
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 workflow connects to an AskOne MCP server and reads poll results and participant-submitted Q&A/word cloud content from audience members, creating an indirect prompt injection vector.
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 references an external MCP endpoint and CLI package (`https://askone.org/api/mcp` and `phuryn/askone`) as operational setup and runtime dependencies, which lack strong official provenance and present an unverified third-party risk tier.
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.