gsd-review
What this skill does
The skill 'gsd-review' is designed to invoke external AI CLIs (such as Gemini, Claude, Codex, etc.) to perform peer reviews of phase plans. It collects feedback from these reviews and writes the resul
github/open-gsd - Data Exfiltration - 7.1k stars
Threat analysis
Skill info
pkg:github/open-gsd/gsd-core@a5180d9?skill=gsd-reviewAssessments (1)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill invokes external AI CLIs (e.g., Gemini, Claude, etc.) to review phase plans. If these external CLIs are not properly secured or if the communication with them is not encrypted, there is a riBadge
Add the Anomity scan badge for gsd-review 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 gsd-review? Report an issue or request a rescan.
