bitv-oeffentliche-stellen
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and logic are consistent with its stated purpose of providing legal analysis for digital accessibility. No obfuscation, persistence mechanisms, or credential harvesting patterns were found.
- [COMMAND_EXECUTION]: The skill utilizes a local Python utility (
scripts.legal_calc.cli) to perform deterministic arithmetic for legal deadlines (e.g., the one-month response window under § 12b BGG). This command execution is restricted to local environment utilities for arithmetic purposes. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data, including accessibility statements, external audit reports, and user feedback messages, to perform its auditing function. While this creates a potential attack surface for indirect prompt injection, it is central to the tool's diagnostic utility. Mandatory evidence chain: 1. Ingestion points: input fields for external reports, statements, and user messages defined in SKILL.md. 2. Boundary markers: absent. 3. Capability inventory: execution of local calculation scripts. 4. Sanitization: absent.
Audit Metadata