mvpfy-problem
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process external context data to populate a problem-mapping template, creating a potential surface for indirect prompt injection.
- Ingestion points: In
SKILL.md, the agent is instructed to 'Leia o contexto atual' (Read the current context), which involves processing potentially untrusted external information. - Boundary markers: There are no explicit delimiters or 'ignore' instructions provided to the agent to help it differentiate between the user-provided context and its own logical constraints.
- Capability inventory: The skill's capabilities are limited to information synthesis and writing results to a local
MVP.mdfile. - Sanitization: No input validation or sanitization procedures are defined for the ingested data.
Audit Metadata