ray-consult
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to provide structured consulting guidance. Analysis of the instructions and referenced files shows no evidence of malicious intent or hidden capabilities. No external network requests or unauthorized file access patterns were found.- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as due diligence materials and interview records, which represents a surface for indirect prompt injection.
- Ingestion points: Untrusted organizational data is processed through the
/ray-consulttrigger in SKILL.md. - Boundary markers: There are no explicit technical delimiters (e.g., XML tags or special tokens) defined to isolate untrusted data from the system instructions.
- Capability inventory: The skill generates diagnostic reports and blueprints but does not demonstrate capabilities for executing shell commands, performing network operations, or invoking dangerous tools.
- Sanitization: The 'Requirement Archaeology' method defined in the instructions serves as a logical validation step to cross-check input claims against evidence, reducing the risk of being misled by injected content.
Audit Metadata