Multi-AI research using available external providers (Double Diamond Discover phase)
70%
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
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/flow-discover/SKILL.mdThe canonical home for this skill is flow-discover in nyldn/claude-octopus
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 required workflow dispatches the user's research topic to external AI providers and fetches external web content (via `validate_external_url`/`wrap_untrusted_content`), so the agent ingests outsider-authored pages and search results it chose to retrieve, but no outsider can push text into a queue or feed the workflow monitors.
nyldn/claude-octopus
9a6967a
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.