listingsapi
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external business data, reviews, and posts from the ListingsAPI service. Ingestion points: Data is retrieved through tool calls like reviews_list and listings_premium in SKILL.md. Boundary markers: The skill does not specify the use of clear delimiters or instructions to ignore embedded commands within the ingested content. Capability inventory: The agent is instructed to perform write operations, including posting review replies and updates to locations. Sanitization: No content filtering is mentioned, although the skill requires explicit user approval before publishing writes.
- [SAFE]: The skill consists of workflow instructions and does not bundle any executable scripts, binaries, or third-party dependencies.
- [SAFE]: Authentication is managed via secure browser-based OAuth or environment variables, with explicit instructions to avoid hardcoding credentials.
Audit Metadata