crypto-technical
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external, third-party websites such as TradingView and Coinglass using WebSearch and WebFetch. Because TradingView contains user-generated content (such as public trading ideas and descriptions), this creates a surface where an attacker could place malicious instructions intended for the agent to follow during the analysis process. The skill does not define specific boundary markers or instructions to sanitize this fetched content.
- Ingestion points: WebSearch and WebFetch directives in SKILL.md for fetching market and indicator data.
- Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate external data from the agent's core instructions.
- Capability inventory: The agent has the ability to search the web, fetch external content, and write data to new files (CRYPTO-TECHNICAL-[TOKEN].md).
- Sanitization: No sanitization, validation, or filtering mechanisms are described for the external content retrieved during the data collection phase.
Audit Metadata