shotation-screenshot-director
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the 'shotation' CLI tool to manage the screenshot production lifecycle. It executes various commands such as
shotation app-storefor web capture,shotation capturefor native screens, andshotation listing renderfor designing cards. - [INDIRECT_PROMPT_INJECTION]: The agent is instructed to read the application's codebase to identify brand colors, fonts, and the primary features of the app. This ingestion of untrusted local data represents a surface for indirect prompt injection if the codebase contains malicious instructions intended to divert the agent's behavior.
- Ingestion points: Application codebase (SKILL.md Step 1) and captured app screens (SKILL.md Step 2).
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading external codebase files.
- Capability inventory: The skill has the ability to execute shell commands via the
shotationtool and write configuration or design files such asdesign.mdandshotation.listing.json. - Sanitization: No explicit sanitization or validation of the data extracted from the application codebase is mentioned in the workflow.
Audit Metadata