lightcraft-photo-export
Warn
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration in references/craft-command-evidence.json points to an external download of a Windows portable binary (lightcraft-cli.exe) from the storytold/lightcraft repository.
- [COMMAND_EXECUTION]: The skill instructions in SKILL.md and references/craft-methods.md direct the agent to execute shell commands using the lightcraft-cli tool to query libraries and export files.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted image files and metadata.
- Ingestion points: Data enters via open_file (SKILL.md) and catalog.query (references/craft-methods.md).
- Boundary markers: None identified in the skill instructions to protect against instructions embedded in metadata.
- Capability inventory: Includes command_run for execution and app.export for file writing.
- Sanitization: The skill includes instructions to validate IDs and parameters against a defined schema before execution.
Audit Metadata