mcore-create-issue

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs and executes multiple shell commands using the GitHub CLI (gh). Variables such as <run_id>, <job_id>, and <pr_number> are interpolated into these commands. If the agent does not properly sanitize these inputs when extracting them from a user-provided URL, it could lead to command injection if a maliciously crafted URL is processed.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes external content from GitHub Actions logs. These logs are used to generate the body of a new GitHub issue. Malicious text within a failing test's output could theoretically influence the agent's behavior during the issue creation process.
  • Ingestion points: The skill fetches raw CI logs via gh api in SKILL.md (Step 3).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the logs are present; snippets are quoted verbatim.
  • Capability inventory: The skill has the capability to search for, create, and assign GitHub issues (gh issue create).
  • Sanitization: No evidence of sanitization or filtering of the log content was found prior to its inclusion in the issue template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:41 PM
Security Audit — agent-trust-hub — mcore-create-issue