django-debug
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of several well-known and standard Python packages from the official PyPI registry, including
django-debug-toolbar,django-extensions, andsentry-sdk. - [DATA_EXFILTRATION]: The skill contains a diagnostic step to print
settings.DATABASESwithin a Django shell. While this command exposes database credentials (host, username, password) to the terminal output, it is a standard diagnostic practice in local development environments and is consistent with the skill's primary purpose of debugging. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external context from a file named
.agents/django-project-context.md. This represents a potential attack surface where untrusted data could influence agent behavior. - Ingestion points:
.agents/django-project-context.md(read-only context) - Boundary markers: None identified
- Capability inventory: Package installation (
pip), shell command execution (manage.py), and file system read access - Sanitization: No specific sanitization or validation of the ingested context file is documented
Audit Metadata