issue-grouping

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Handling External Content: The skill fetches issue data from the vscode repository to categorize them.
  • Ingestion points: Issue content is retrieved via the GitHub MCP server in Steps 1 and 3 of SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters for separating issue content from the subagent's rules.
  • Capability inventory: The skill uses repository read capabilities and performs local file writing to 'categorized-issues.md'.
  • Sanitization: No explicit sanitization or filtering of fetched text is specified.
  • Context: Ingesting repository issues is central to this skill's functionality, and the data is sourced from a well-known repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 07:52 PM
Security Audit — agent-trust-hub — issue-grouping