scb-profile-router

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources which presents a surface for indirect prompt injection.
  • Ingestion points: Data enters the skill context through the url_or_path input, which is used to crawl web pages or parse local files for structural and semantic signals.
  • Boundary markers: The instructions do not specify the use of delimiters (like triple backticks or XML tags) or system-level warnings to the agent to ignore instructions embedded within the processed content.
  • Capability inventory: While this specific skill only generates a manifest, its output is explicitly designed to drive downstream automated tasks in other skills such as scb-execution-planner, which may have higher-privilege capabilities.
  • Sanitization: There is no mention of sanitizing or escaping the content extracted from the target URLs or files before it is used to determine routing logic or passed to the output JSON manifest.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:16 PM
Security Audit — agent-trust-hub — scb-profile-router