django-perf-review
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides standard instructional content and code examples for optimizing Django ORM performance (e.g., resolving N+1 queries, adding database indexes, and batching writes). No malicious patterns, obfuscation, or unauthorized data access were identified.\n- [EXTERNAL_DOWNLOADS]: Mentions the author's GitHub repository (
github.com/sickn33/antigravity-awesome-skills) for provenance and attribution. This reference to a well-known service is documented neutrally and does not involve the execution of untrusted remote code.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for analyzing external codebases, which presents an attack surface for indirect prompt injection.\n - Ingestion points: Ingests user-provided Django source files, templates, and serializers for performance auditing (SKILL.md).\n
- Boundary markers: Absent; the skill does not specify the use of delimiters or instructions to ignore embedded commands in the reviewed code.\n
- Capability inventory: Configured for use with tools like
claude-codeandcodex-cli, which typically possess filesystem and command execution capabilities.\n - Sanitization: No sanitization or validation of the ingested code content is defined.
Audit Metadata