apify-trend-analysis
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides shell commands for fetching Actor schemas via
mcpcand running analysis scripts using Node.js.\n- [EXTERNAL_DOWNLOADS]: Therun_actor.jsscript andSKILL.mdfetch configuration and data from Apify's official domains (api.apify.comandmcp.apify.com), which are well-known technology services.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from social media platforms, creating a surface for indirect prompt injection.\n - Ingestion points: External trend data from Instagram, TikTok, Facebook, YouTube, and Google Trends (processed in
SKILL.mdvia Actor results).\n - Boundary markers: Absent; the instructions do not include delimiters or warnings for the agent to ignore instructions embedded in the external content.\n
- Capability inventory: The skill has file-write capabilities via
fs.writeFileSyncinrun_actor.js.\n - Sanitization: No sanitization or escaping is performed on the scraped data before it is presented to the agent for analysis.
Audit Metadata