gh-issues

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the GitHub CLI and standard shell utilities to automate issue management.
  • Evidence: Frequent use of gh issue, gh api, and shell operations like xargs and cat in SKILL.md and README.md.
  • Context: These operations are consistent with the skill's primary purpose of providing a CLI-based workflow.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection because it reads and processes external data as instructions.
  • Ingestion points: The skill fetches issue comments using gh issue view to restore AI session context (as described in SKILL.md).
  • Boundary markers: The session context is delimited by <!-- AI-CONTEXT:START --> and <!-- AI-CONTEXT:END --> tags, which provide weak isolation against adversarial input.
  • Capability inventory: The skill has the ability to execute shell commands (gh, git) and write to local files (.ai-context.md).
  • Sanitization: No sanitization or explicit instructions to ignore embedded commands within fetched comments are provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 04:36 PM
Security Audit — agent-trust-hub — gh-issues