alterlab-vcd-poster-designer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external web searches and local project files, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill's workflow explicitly instructs the agent to search the web for visual references and trends, and to read existing project files such as brand guidelines and image assets.
- Boundary markers: The instructions lack specific delimiters or "ignore embedded instructions" warnings to prevent the agent from executing commands that might be hidden within the processed data.
- Capability inventory: The agent has the authority to perform web searches, read local project files, and write multiple types of markdown specification files to the project directory.
- Sanitization: The skill does not provide mechanisms for sanitizing or validating the content retrieved from external sources before it is processed or incorporated into outputs.
Audit Metadata