bfsg-dienstleistung-ecommerce
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data, including technical reports and consumer complaints. This creates a theoretical surface where malicious instructions embedded in those documents could attempt to influence the agent's behavior.\n
- Ingestion points: Inputs defined in
SKILL.mdsuch as 'Technischer Stand', 'Vorhandene Barrierefreiheitsinformationen', and 'Vorliegender Verbraucher- oder Verbandsantrag'.\n - Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore potentially malicious embedded content in the ingested data.\n
- Capability inventory: The skill utilizes a local Python script (
scripts.legal_calc.cli) via shell execution to perform date calculations.\n - Sanitization: No explicit sanitization or escaping of external content is mentioned before it is processed or used in logic.\n- [DYNAMIC_EXECUTION]: The skill involves the execution of a local CLI tool (
scripts.legal_calc.cli) usingpython -m. This is used to calculate legal deadlines based on input data.
Audit Metadata