apify-trend-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scrapes data from external sources like TikTok, Instagram, and Google Trends. This untrusted content is then summarized by the agent, creating a surface for instructions embedded in trend data to influence the agent.
- Ingestion points: Data is retrieved from the Apify API in
run_actor.js. - Boundary markers: The skill lacks explicit instructions or delimiters to isolate untrusted content from the agent's logic during the summarization step.
- Capability inventory: The agent can execute shell commands and write files.
- Sanitization: No natural language filtering is applied to the fetched data before processing.
- [COMMAND_EXECUTION]: The workflow requires the execution of the
mcpcCLI tool and a custom Node.js script, providing the agent with broad execution capabilities within the local environment. - [DATA_EXFILTRATION]: The
run_actor.jsscript passes theAPIFY_TOKENas a URL query parameter (?token=...). While communication is with the official Apify API, this practice is less secure than using HTTP headers and may lead to token exposure in log files or intermediate network metadata.
Audit Metadata