brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
73%
Does it follow best practices?
Impact
74%
1.17xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./src-tauri/experts/skills/brainstorming/SKILL.mdThe canonical home for this skill is brainstorming in obra/superpowers
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
In `scripts/server.cjs` the brainstorming visual companion’s WebSocket handler (`handleMessage`) parses and then writes user-provided JSON event fields (including `event.choice` and associated text) into `$STATE_DIR/events`, which the next turn reads to inform the agent; this means outsider-authored free text can be injected into the runtime-consumed event stream.
- Repository
arwei944/codeg
- Revision
e83e543
- 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.