gewerbeanzeige-reisegewerbe
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data such as activity descriptions and official legal notices (Untersagungs- oder Bußgeldbescheid) provided by the user.
- Ingestion points: Defined in the 'Eingaben' section of SKILL.md.
- Capability inventory: The skill utilizes a local script (scripts.legal_calc.cli) via subprocess to calculate legal deadlines based on the ingested data.
- Boundary markers: There are no explicit instructions or markers to distinguish between the skill's instructions and the external data being processed.
- Sanitization: No explicit sanitization or validation of the input data is mentioned before it is processed by the agent or passed to the calculation script.
- [COMMAND_EXECUTION]: The skill provides templates for executing a local Python script (scripts.legal_calc.cli) to perform legal calculations.
- Evidence: The 'Deterministische Berechnung' section in SKILL.md contains bash code blocks that pass user-supplied dates and parameters to the script. While these are presented as templates for the agent, there is a risk of command injection if the agent interpolates unsanitized user input directly into these command strings.
Audit Metadata