ascendc-operator-doc-gen
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface detected. The skill processes instructions and data from various project files (design.md, source code, test scripts) to generate documentation and write files, which could be exploited if those files contain malicious instructions.\n
- Ingestion points: csrc/register.cpp, csrc/ops.h, design.md, op_host/op_name.cpp, and tests/test_op_name.py.\n
- Boundary markers: Absent; the skill does not instruct the agent to use delimiters or specific safety markers when handling the ingested content.\n
- Capability inventory: File reading for source analysis and file writing for README.md generation.\n
- Sanitization: No sanitization, validation, or escaping of the content read from files is specified.
Audit Metadata