NYC

drone-cv-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses an attack surface for indirect prompt injection via external data ingestion.
  • Ingestion points: mcp__firecrawl__firecrawl_search and WebFetch tools allow the agent to retrieve untrusted content from the web.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the skill configuration.
  • Capability inventory: The agent has access to Bash(python:*, pip:*), Write, and Edit tools, allowing for file modification and command execution based on processed data.
  • Sanitization: No evidence of sanitization or validation of the ingested data before use in prompts or commands was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:54 PM