screenshot
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests external data, creating a surface for indirect prompt injection. 1. Ingestion points: Web pages and UI fixtures (described in SKILL.md). 2. Boundary markers: None specified; the workflow relies on manual inspection to verify output. 3. Capability inventory: Instructions include running repository-specific build/preview commands and writing to the asset directory (described in SKILL.md). 4. Sanitization: Explicitly instructs the agent to check for and exclude credentials, customer data, and internal hostnames from captured images (described in SKILL.md).
- [COMMAND_EXECUTION]: The workflow directs the agent to run documentation build and preview commands found within the project repository.
- [NO_CODE]: The skill consists exclusively of markdown instructions and does not contain any executable scripts or binary files.
Audit Metadata