apify-brand-reputation-monitoring
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use shell commands to manage Apify actors, fetch schemas, and run monitoring tasks via the
run_actor.jsutility script.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the@apify/mcpcCLI tool, which is the official client for Apify, a well-known service for web automation and data extraction.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data retrieved from various third-party websites (reviews, comments, and social media posts).\n - Ingestion points: Data is fetched from Apify datasets and processed by the
run_actor.jsscript in thereference/scripts/directory.\n - Boundary markers: The script uses
csvCelllogic to delimit data in CSV exports, preventing structural confusion in the output files.\n - Capability inventory: The skill has the capability to perform network requests (
fetch) and write results to the local filesystem (writeFileSync).\n - Sanitization: The
run_actor.jsscript includes specific logic to escape control characters (=,+,@,-) in output data to prevent CSV formula injection attacks.
Audit Metadata