coding-python
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on external source code and templates, providing a potential surface for indirect prompt injection attacks where instructions could be hidden in processed data.
- Ingestion points: The skill triggers for and reads Python files (.py), Flask blueprints, and Jinja2 templates (.jinja, .html) as described in SKILL.md.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded directives within the source code are specified.
- Capability inventory: The agent has the capability to write and modify project files and define test execution logic for pytest (SKILL.md).
- Sanitization: There are no instructions for sanitizing or validating the content of the files being edited.
Audit Metadata