Skills
skills/yigitkonur/skills-by-yigitkonur/run-issue-tree/Gen Agent Trust Hub

run-issue-tree

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests data from external GitHub issues to generate prompts for subagent execution, creating a surface for indirect prompt injection.
  • Ingestion points: GitHub issue bodies and metadata are fetched using gh api calls in scripts/dispatch-wave.sh, scripts/read-tree.sh, and scripts/issue-tree-status.sh.
  • Boundary markers: The skill uses standardized ownership and completion protocol markers in issue bodies as defined in references/issue-body-template.md to help subagents distinguish instructions from data.
  • Capability inventory: The skill dispatches tasks to subagents, executes gh CLI commands to modify repository state, and writes prompt files to the local file system.
  • Sanitization: The scripts/validate-issue-body.sh script provides sanitization by checking for tool-specific command patterns and vague criteria in issue bodies before they are processed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:36 PM
Security Audit — agent-trust-hub — run-issue-tree