Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm or scope what to build. Not for executing already-specified work. Use ce-pov for a verdict on adopting a named external technology.
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/ce-brainstorm/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill's visible instructions serve its advertised brainstorming purpose, but the Codex sandbox-escalation request (full command escalation for a detached worker that inherits launch permissions) weakens a protection beyond what the elevation task strictly needs, so it is risky toward the user though disclosed and not malicious.
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.
Required Phase 1.1 pack discovery has the agent read frontmatter and constraints from user-configured Compound Pack roots, which can be third-party git or community packs, so this is low-risk exposure: the agent reads them without selecting a specific item, but the attacker cannot force delivery, and the opt-in Slack researcher is not required.
EveryInc/compound-engineering-plugin
ee46dde
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.