develop

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issue titles, descriptions, and comments which could contain adversarial instructions.\n
  • Ingestion points: External content is fetched using gh issue view in Step 1.\n
  • Boundary markers: The instructions do not provide explicit delimiters or 'ignore previous instructions' warnings to isolate ingested data from the agent's core logic.\n
  • Capability inventory: The skill has broad capabilities, including writing code, executing shell commands (pnpm, git), and pushing changes to remote repositories.\n
  • Sanitization: No sanitization or validation steps are present to filter content from the issue before the agent processes it.\n- [COMMAND_EXECUTION]: The skill uses shell commands for project management (GitHub CLI), version control (Git), and build processes (pnpm). These are appropriate for the developer context but constitute a significant execution surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:19 PM
Security Audit — agent-trust-hub — develop