easyslides-clarify
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
scripts/easyslides.pyto handle project initialization and record user decisions. This is part of the intended integration with the EasySlides tool. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from user conversations and uploaded file metadata to determine presentation requirements, creating an attack surface for indirect injection.
- Ingestion points: The skill reads conversation history, source metadata, and user-provided answers.
- Boundary markers: No specific delimiters are defined to separate untrusted data from the agent's instructions.
- Capability inventory: The skill can execute local scripts and write to project-specific JSON and Markdown files.
- Sanitization: There is no mention of sanitization or validation of user-provided strings before they are recorded as state or passed to CLI tools.
Audit Metadata