cross-ref
What this skill does
The skill 'cross-ref' is designed to find duplicate GitHub PRs and missing links between GitHub issues and PRs. It uses parallel subagents to analyze PRs and issues, cluster findings, and offer action
github/leoyeai - Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=cross-refAssessments (2)
Exfiltration
Exfiltration via local-llm-review
scripts/fetch-data.sh
The script fetches PR and issue metadata from the GitHub API and stores it in the workspace directory. This could potentially expose sensitive information if the workspace directory is not properly seRate Limiting
Rate Limiting via local-llm-review
scripts/post-comments.sh
The script uses jitter-based rate limiting to post comments. If not properly configured, this could lead to unintended behavior or potential abuse of GitHub's API rate limits.Badge
Add the Anomity scan badge for cross-ref 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 cross-ref? Report an issue or request a rescan.
