arbeitszeugnis

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided certificate text, which is an untrusted external source.
  • Ingestion points: The skill explicitly requests "Vorliegendes Zeugnis im Volltext" (existing certificate text) as a primary input in SKILL.md.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined for the input data.
  • Capability inventory: The skill leverages sub-agents (researcher.md, drafter.md, reviewer.md) which perform complex tasks and may have access to further tools defined in their respective configurations.
  • Sanitization: There is no evidence of input sanitization or filtering for the text being analyzed.
  • [COMMAND_EXECUTION]: The test.md file contains instructions to execute a local Python script (python scripts/eval.py) for evaluation purposes. This is a standard development practice and does not represent an automated runtime execution vulnerability.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:57 PM