pr-address-comments
What this skill does
The skill is designed to help users address GitHub PR comments for the Gemini CLI. It uses the `gh` CLI tool and fetches PR information via a GraphQL query to analyze comments and reviews.
github/google-gemini - Exfiltration of Sensitive Data - 106.4k stars
Threat analysis
Skill info
pkg:github/google-gemini/gemini-cli@eef19f2?skill=pr-address-commentsAssessments (2)
Exfiltration of Sensitive Data
Exfiltration of Sensitive Data via local-llm-review
scripts/fetch-pr-info.js
The script sends a GraphQL query to a GitHub API endpoint, which may include sensitive information such as the current git branch name. If the script is not properly secured, it could potentially expoInsecure API Usage
Insecure API Usage via local-llm-review
scripts/fetch-pr-info.js
The script uses `execAsync` to run shell commands, which could be vulnerable to command injection if user input is not properly sanitized. This could allow an attacker to execute arbitrary commands onBadge
Add the Anomity scan badge for pr-address-comments 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 pr-address-comments? Report an issue or request a rescan.
