service-blueprint
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing untrusted user data without sufficient safeguards.
- Ingestion points: Data provided by the user during the 'Paso 1 -- Detectar Contexto' and 'Paso 3 -- Recopilar Datos' sections (e.g., persona details, actions, thoughts, and frustrations).
- Boundary markers: Instructions do not define specific delimiters or instructions to ignore embedded commands within user-provided strings when generating the map.json file.
- Capability inventory: The skill performs file system write operations (map.json) and dispatches secondary agents (renderer.md, persona-builder.md) which process the ingested data.
- Sanitization: There is no evidence of input validation, escaping, or filtering for user-provided content before it is stored or rendered.
Audit Metadata