leiloeiro-avaliacao
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process data from external real estate portals, creating a surface for potential injection of malicious instructions via user-generated listings.
- Ingestion points: The
references/detailed-guide.mdfile instructs the agent to research and collect data from external sites including ZAP Imóveis, Viva Real, OLX, and Quinto Andar. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the fetched data defined in the skill's guidelines.
- Capability inventory: The skill includes
scripts/governance.py, which has the capability to perform file write operations (creating and appending toaction_log.jsonl). - Sanitization: The skill does not define any sanitization, filtering, or validation steps for the content retrieved from external websites before it is processed by the agent.
Audit Metadata