real-estate-deal-negotiation-strategist
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing external information, including property listings, market transaction data (DLD), and party motivations. This represents an attack surface where untrusted data could influence agent behavior.
- Ingestion points: External data enters the context during 'Step 1: Pre-Negotiation Intelligence' and 'Step 2: Offer Engineering' in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The agent instructions focus on strategy generation and document preparation. The included shell script (scripts/run.sh) is a standard wrapper for the platform's skill runner and does not perform dangerous operations.
- Sanitization: The skill does not implement validation or sanitization for the market data it processes.
Audit Metadata