apify-local-business-leads-osm
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
apifyCLI (apify actors call,apify actors info) to execute remote logic on the Apify platform. This is the primary intended function of the skill for data extraction. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it crawls external business websites and processes the results.
- Ingestion points: Data is ingested from OpenStreetMap and individual business websites during the crawl process (referenced in SKILL.md Step 4 and 5).
- Boundary markers: The skill defines specific boundaries in the 'Out of scope' section, distinguishing its functionality from other tools like Google Maps scrapers.
- Capability inventory: The agent can execute shell commands via the
apifyCLI to trigger Actors and retrieve dataset items. - Sanitization: There is no explicit mention of sanitization for the crawled content before it is delivered as a lead table.
- [CREDENTIALS_UNSAFE]: Benign usage. The skill explicitly instructs the user to handle the
APIFY_TOKENvia environment variables or standard authentication headers rather than hardcoding them, which aligns with security best practices.
Audit Metadata