arc-planning-github-issues

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using the GitHub CLI (gh) to retrieve issue metadata, post comments, and interact with project boards. It also uses git to create new feature branches. These actions are aligned with the skill's stated purpose of automating GitHub workflow tasks.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it processes untrusted external data.
  • Ingestion points: The command gh issue view <number> --json title,body,labels imports user-controlled text from GitHub issues into the agent's context (SKILL.md).
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat the imported issue content as data rather than instructions.
  • Capability inventory: The agent has the ability to execute shell commands (gh, git) and write information back to the repository via comments.
  • Sanitization: The skill does not include steps to sanitize or validate the issue body before the agent analyzes it for planning purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 02:52 AM
Security Audit — agent-trust-hub — arc-planning-github-issues