local-falcon-tool
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a potential surface for indirect prompt injection.
- Ingestion points: Ingests external business reviews via
getLocalFalconReviewsAnalysisReportand competitor ranking data viagetLocalFalconCompetitorReportinSKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the data retrieved from the Local Falcon API.
- Capability inventory: The skill possesses the ability to execute SEO-related commands and campaigns via MCP tools such as
runLocalFalconScan,createLocalFalconCampaign, andaddLocationsToFalconGuard. - Sanitization: There is no mention of sanitizing or escaping the user-generated content (reviews) before it is processed by the agent.
Audit Metadata