skills/promovaweb/mvpfy/mvpfy-problem/Gen Agent Trust Hub

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.md file.
  • Sanitization: No input validation or sanitization procedures are defined for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 12:19 PM
Security Audit — agent-trust-hub — mvpfy-problem