mobile-app-launch-checklist
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by using user-provided strings (specifically the 'App name' input) to construct a local filename (
LAUNCH-CHECKLIST-{AppName}.md). A malicious user could provide a name containing path traversal sequences or special characters to attempt to write the checklist to unintended locations. - Ingestion points: User-provided 'App name' input defined in
SKILL.md. - Boundary markers: No delimiters or instructions are used to separate the user-provided app name from the rest of the file generation logic.
- Capability inventory: The skill utilizes a file-write capability to save the generated checklist to the project root.
- Sanitization: There is no evidence of validation or sanitization of the 'App name' before it is interpolated into the file path.
Audit Metadata