alterlab-vcd-exhibition
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external project documentation, which creates a potential surface for indirect prompt injection. \n- Ingestion points: The instructions direct the agent to read external project files such as venue floor plans, brand guidelines, event briefs, and prior documentation (SKILL.md). \n- Boundary markers: The skill lacks explicit instructions to treat data within these external files as untrusted or to ignore any embedded behavioral instructions. \n- Capability inventory: The agent possesses file-read, file-write, and web search capabilities, which could be leveraged if malicious instructions were successfully injected via the ingested files. \n- Sanitization: There are no defined processes for sanitizing, validating, or filtering the content of the external files before the agent processes them.
Audit Metadata