find-local-clients

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (places_search.py, site_check.py) provided in the package to process business data. It also attempts to call a script located in a sibling directory (../start-here/scripts/brand_context.py) to load agency-specific branding information, using a fallback method if the file is unavailable.- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from multiple external sources.
  • Ingestion points: HTML content from scraped business sites, search engine result snippets, and business descriptions from the Google Places API.
  • Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore potentially malicious embedded content in the ingested web data.
  • Capability inventory: The skill possesses the ability to write to the local file system, perform network operations, and execute local scripts based on the results of its analysis.
  • Sanitization: There is no evidence of sanitization or filtering of the external content before it is presented to the agent for evaluation.- [EXTERNAL_DOWNLOADS]: The skill makes network requests to the Google Places API (a well-known service) and to arbitrary third-party business websites to gather auditing information and lead details.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 04:01 PM