skills/avdlee/rocketsimapp/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted user input to perform tool operations and guide background tasks.
  • Ingestion points: User descriptions of bugs and issues are collected conversationally in the "Listen and lightly clarify" section of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or instructions to treat user-provided data as untrusted, which could lead the agent to follow instructions embedded within a bug report.
  • Capability inventory: The skill utilizes the gh command-line tool for remote issue creation and triggers a codebase exploration subagent (subagent_type=Explore).
  • Sanitization: No sanitization, filtering, or escaping mechanisms are described for the user-provided input before it is used in the gh issue create command or by the exploration agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 09:42 PM
Security Audit — agent-trust-hub — qa