launchpad
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill reference s documentation and best practice s hosted on official domain s associated with Google, Anthropic, and OpenAI (e.g., google.com, claude.com, openai.com). The se reference s originate from trusted provider s and are used neutrally.
- [PROMPT_INJECTION]: The skill processe s untrusted input in the form of file s and UR L s during its intake phase, creating a surface for in direct prompt injection. Ingestion point s: SKILL.md and intake/flow.md. Boundary marker s: Absent. Capability inventory: The agent use s Bash, Write, Edit, and WebFetch tool s. Sanitization: No specific sanitization or filtering of external content is im plemented.
Audit Metadata