lightcraft-landscape-develop
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill metadata references a remote portable ZIP archive containing the LightCraft CLI executable hosted on GitHub (storytold/lightcraft).
- [COMMAND_EXECUTION]: The workflow involves executing photo manipulation commands (e.g., develop.set, app.export) via a local CLI or a specialized command_run tool interface.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes photo metadata and development settings which could potentially contain malicious instructions, creating a vulnerability surface.
- Ingestion points: Data is retrieved via catalog.query and develop.get commands in references/craft-steps.json.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used for data returned by the tool.
- Capability inventory: The skill possesses file system write access through the app.export command and generic command execution via command_run and a local CLI.
- Sanitization: There is no evidence of explicit sanitization or filtering of the ingested external photo settings before they are used in subsequent commands.
Audit Metadata