propertyguru-com-sg
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites (propertyguru.com.sg) via tools like
propertyguru_com_sg__read_page. This ingestion of untrusted data creates a potential surface for indirect prompt injection, where instructions hidden on a webpage could attempt to influence the agent's behavior. - Ingestion points: Data is ingested through tools defined in
SKILL.md, includingpropertyguru_com_sg__get_property_for_sale,propertyguru_com_sg__get_agent_profile_active_listings, andpropertyguru_com_sg__read_page. - Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded within the retrieved property data.
- Capability inventory: The skill facilitates remote data retrieval through the Unbrowse MCP server but does not include capabilities for local file writing, system command execution, or arbitrary code evaluation.
- Sanitization: There are no instructions for sanitizing or escaping the content retrieved from the external site before it is processed by the agent.
Audit Metadata