hypo-generator
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites to perform its primary function of discovery and hypothesis generation. This creates a potential surface for indirect prompt injection where malicious content on a target site could attempt to manipulate the agent's logic or output.
- Ingestion points: SKILL.md (Phase 1
- Discovery via WebFetch of provided URLs).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or explicit 'ignore' instructions for the fetched content.
- Capability inventory: The skill primarily uses data extraction and text generation tools. No evidence of shell execution, file-system writes, or sensitive data exfiltration was found in the analyzed files.
- Sanitization: Absent. No content validation or sanitization rules are defined for the fetched data.
Audit Metadata