cc-project-init
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests the current state and structure of the user's repository to determine how to initialize configuration files. This processing of potentially untrusted data from the repository files creates a surface for indirect prompt injection.
- Ingestion points: Repository file contents and directory structure (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded content in the scanned files.
- Capability inventory: The skill is authorized to create and update directories (.codex/tasks, .codex/templates) and project-level files (AGENTS.md).
- Sanitization: No explicit sanitization or validation of the ingested repository data is described.
Audit Metadata