review-intelligence-digest

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The instructions describe running local Python scripts for scraping (scrape_reviews.py) and scheduling (run_skill.py). These are standard operational commands for the skill.
  • [EXTERNAL_DOWNLOADS]: The skill uses the Apify API to fetch content from third-party review platforms including G2, Capterra, and Trustpilot.
  • [PROMPT_INJECTION]: The skill processes untrusted external data, creating an indirect prompt injection surface.
  • Ingestion points: Review bodies and titles scraped from external websites as defined in SKILL.md Phase 1.
  • Boundary markers: Absent; data is fed to LLM analysis without specified delimiters or instructions to ignore embedded prompts.
  • Capability inventory: Local script execution and file system writes to the clients/ directory.
  • Sanitization: No validation or filtering of the scraped review content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 02:42 PM