thiel
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified. The skill ingests untrusted data from the web using WebSearch and WebFetch and passes this data to specialized agents (e.g., Market Framer) without specific security delimiters. These agents have access to powerful tools like Bash and Write, which could be targeted by malicious instructions hidden on external websites.
- Ingestion points: Untrusted content from the web enters the agent context during market research phases.
- Boundary markers: Absent; the prompts do not explicitly instruct agents to ignore instructions embedded in the retrieved web content.
- Capability inventory: The skill and its spawned agents have access to Bash, Write, Edit, and Agent tools.
- Sanitization: No content validation or sanitization is performed on the data retrieved from external sources before processing.
Audit Metadata