setup-issue-tracker

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines and uses command-line operations through the GitHub CLI (gh) and Linear tools to manage issue lifecycles, including creation, state updates, and dependency tracking.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests content from external issue tracker bodies and titles (e.g., from GitHub or Linear). It employs HTML comment markers (such as <!-- triage-issues:spec:start -->) to bound AI-managed sections, providing a mitigation against the agent acting on malicious instructions embedded in human-written text. Ingestion points: external issue tracker descriptions and titles; Boundary markers: HTML comments are used to isolate AI content; Capability inventory: includes shell command execution (via gh and Linear tools) and local file writes (to AGENTS.md, CLAUDE.md, and docs/issue-tracker.md); Sanitization: involves structural bounding and verification of body content after writing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 08:26 AM