django-project-context
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data to generate a summary, creating a potential surface for indirect prompt injection if source files contain malicious instructions.
- Ingestion points: Local codebase files including settings.py, requirements.txt, and models.py.
- Boundary markers: The generated context document does not use specific delimiters to isolate external content.
- Capability inventory: The skill involves reading project files and writing a markdown summary to the local filesystem.
- Sanitization: There is no explicit sanitization of data extracted from project source files before it is written to the context document.
- [NO_CODE]: The skill contains only instructional markdown and does not ship with any executable scripts, which significantly reduces the risk of direct command execution or local attacks.
Audit Metadata