review-intelligence-digest

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a subprocess command to execute a local Python script (scrape_reviews.py) for review collection as part of its primary functionality.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted review text from external websites into the agent context for analysis.
  • Ingestion points: Public review data from G2, Capterra, and Trustpilot (SKILL.md).
  • Boundary markers: Absent; reviews are interpolated into the prompt without explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: Writes analysis results to local markdown files (SKILL.md).
  • Sanitization: No sanitization of the scraped review content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 10:48 AM