smlib-python-api-maintain
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute local repository scripts for building and testing the library. These include
./repo.sh build,tools/agent/run_smpylib_tests.sh, andpython3 tools/agent/check_smpylib_surface.py. - Evidence: Found in the 'Validation', 'Prerequisites', and 'Common Change Flow' sections of
SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill ingest data from various project files to inform its code generation and review tasks. This represents a potential surface for indirect prompt injection if those files were to contain malicious instructions.
- Ingestion points: Reads C++ headers in
source/SM_API/inc/, documentation insource/SmPyLib/DOCSTRING_STYLE.md, and operation guides in.agents/operations/. - Boundary markers: None explicitly mentioned in the skill instructions.
- Capability inventory: The skill can modify C++ binding files (
.cpp), Python stubs (.pyi), and test files (.py), and it can execute local build and test commands. - Sanitization: No specific sanitization or validation of the ingested header or documentation content is described.
Audit Metadata