ce-pov
What this skill does
The skill 'ce-pov' is designed to form a project-grounded point of view on a subject, such as an external-adoption question, a document, or a set of approaches. It is used for consulting other models
github/everyinc - Privilege Escalation - 24.2k stars
Threat analysis
Skill info
pkg:github/EveryInc/compound-engineering-plugin@d344f7f?skill=ce-povAssessments (2)
Privilege Escalation
Privilege Escalation via local-llm-review
scripts/cross-model-pov.sh
The script uses 'chmod 700' to set permissions on files or directories. While this is a common practice for securing files, the use of '700' permissions may be a red flag if it's applied to files thatTool Misuse
Tool Misuse via local-llm-review
scripts/cross-model-pov.sh
The script contains the command '&& rm -' which appears to be incomplete. This could be a potential risk if it's intended to be used in a way that could lead to unintended file deletions.Badge
Add the Anomity scan badge for ce-pov 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-pov? Report an issue or request a rescan.
