ascendc-operator-testcase-gen
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes design.md, which is a user-controlled file. This creates a surface where an attacker could embed malicious instructions within the design document that the agent might unknowingly incorporate into the generated test cases. 1. Ingestion points: The agent reads from design.md. 2. Boundary markers: The skill lacks explicit delimiters or warnings to the agent to ignore instructions found within the input document. 3. Capability inventory: The skill performs file read and write operations within the ascend-kernel directory. 4. Sanitization: There is no evidence of filtering or sanitizing the content of the design document before it is used to populate templates.
Audit Metadata