context-mode-ops
What this skill does
The skill 'context-mode-ops' is a tool for managing GitHub issues, PRs, releases, and marketing using a parallel subagent system. It is designed to triage issues, review PRs, release versions, and per
github/mksglu - Agent Snooping - 19.8k stars
Threat analysis
Skill info
pkg:github/mksglu/context-mode@37dc25b?skill=context-mode-opsAssessments (1)
Agent Snooping
Agent Snooping via local-llm-review
validation.md
The skill references a file path `~/.gemini/settings.json`, which may contain sensitive configuration data. If the agent is instructed to read or access this file, it could be a risk of snooping or daBadge
Add the Anomity scan badge for context-mode-ops 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 context-mode-ops? Report an issue or request a rescan.
