django-views
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local project configuration files, which represents an ingestion point for potentially untrusted data that could influence agent behavior.
- Ingestion points: The skill directs the agent to read
.agents/django-project-context.mdor.claude/django-project-context.mdto understand project preferences (SKILL.md). - Boundary markers: Absent; there are no instructions to use delimiters or specific warnings to ignore embedded instructions within these context files.
- Capability inventory: The skill facilitates the creation and modification of Django views, models, and URL configurations, which are sensitive code-generation tasks.
- Sanitization: Absent; the instructions do not specify any validation or filtering mechanisms for the data read from the context files.
Audit Metadata