platform-norm-profiler

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes internal utility scripts (scripts/connectors/firecrawl.py and scripts/connectors/tavily.py) to fetch official documentation from the web. These are project-specific connectors and fall within the expected operational scope of the agent's environment.
  • [SAFE]: The skill incorporates explicit security instructions for the agent to treat all fetched documentation and user-pasted text as untrusted input. It specifically warns against following instructions embedded in scraped pages, which is a best-practice defense against indirect prompt injection.
  • [SAFE]: Data operations are restricted to specific, documented paths (references/platforms/ and memory/social/platform-norm-profiler/), maintaining a controlled file system footprint.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 03:38 PM
Security Audit — agent-trust-hub — platform-norm-profiler