ce-plan
What this skill does
The skill 'ce-plan' is a planning tool used to create structured, multi-step plans for software and non-software tasks. It is designed to work with other tools like 'ce-brainstorm' and 'ce-work' to de
github/everyinc - Data Exfiltration - 24.2k stars
Threat analysis
Skill info
pkg:github/EveryInc/compound-engineering-plugin@d344f7f?skill=ce-planAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/elevation-dispatch.sh
The script 'elevation-dispatch.sh' is designed to run a reasoning-heavy step on a user-chosen model via the Claude CLI. It streams NDJSON output, which could potentially be used to exfiltrate data if Excessive Agency
Excessive Agency via local-llm-review
scripts/context.mjs
The script contains a comment that suggests the subagent should be spawned without re-asking the user, which could be interpreted as excessive agency if the user's intent is not properly understood orBadge
Add the Anomity scan badge for ce-plan to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of ce-plan? Report an issue or request a rescan.
