implementing-navigation
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides scripts for processing external configuration files which could be exploited to inject malicious code during the scaffolding process.\n
- Ingestion points: The
scripts/generate_routes.pyandscripts/validate_navigation_tree.jsutilities read fromroutes.yamlandnav-config.jsonrespectively.\n - Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from following instructions potentially embedded in these configuration files.\n
- Capability inventory: These scripts facilitate the generation of Python and JavaScript web routing code. Maliciously crafted input files could result in the production of insecure or backdoored application code.\n
- Sanitization: The generation scripts perform basic string manipulation without rigorous sanitization or validation of the input values before they are used in code templates.
Audit Metadata