apify-trend-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of shell commands using the
mcpcCLI and a local Node.js script (run_actor.js) to interact with the Apify platform. - [DATA_EXFILTRATION]: The script communicates with
https://api.apify.comto manage actor runs and download dataset results. This interaction targets a well-known service and is necessary for the skill's primary functionality. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes and displays content from untrusted external sources like Instagram, TikTok, and YouTube.
- Ingestion points: Data is ingested in
run_actor.jsvia thedisplayQuickAnswerfunction, which fetches dataset items from Apify. - Boundary markers: The skill does not use specific delimiters or instructions to ignore potential commands embedded in the retrieved social media data.
- Capability inventory: The skill uses command-line execution for the
mcpctool and thenoderunner script. - Sanitization: Content is truncated for length before display, but no validation or filtering is performed to identify or neutralize embedded instructions.
Audit Metadata