tia-project-general

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical repository for TIA Portal Openness API documentation. The provided C# code snippets use standard namespaces (Siemens.Engineering) and follow best practices, such as using SecureString for credential handling in references/umac-and-auth.md.
  • [PROMPT_INJECTION]: The skill documents how to ingest data from external project files, which constitutes a potential surface for indirect prompt injection. This is a standard requirement for the skill's purpose but involves reading attacker-controllable fields.
  • Ingestion points: Reading attributes such as project.Comment, project.Name, and project.HistoryEntries (found in references/project-attributes.md and references/language-settings.md).
  • Boundary markers: The reference patterns do not include explicit markers to delimit untrusted project text.
  • Capability inventory: The skill facilitates project creation, modification, and software/hardware compilation via the ICompilable service (found in references/project-lifecycle.md and references/compile.md).
  • Sanitization: No text sanitization or validation logic is demonstrated in the examples when reading project metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 09:56 AM
Security Audit — agent-trust-hub — tia-project-general