appshot-images
Pass
Audited by Gen Agent Trust Hub on May 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's workflow includes ingesting project-specific data which creates a surface for indirect prompt injection.
- Ingestion points: Metadata is read from .appshot-context.json during the extraction phase.
- Boundary markers: The skill does not implement delimiters or safety instructions to prevent the agent from following commands that might be hidden within the ingested metadata.
- Capability inventory: The skill enables the agent to execute shell commands via npx and write files to the local file system.
- Sanitization: There is no requirement for validating or escaping the ingested JSON data before it is incorporated into shell commands or HTML templates.
Audit Metadata