create-project-context
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs standard project management tasks by reading and writing local documentation files within the
.agents/directory. No malicious intent or dangerous patterns were identified. - [DATA_EXPOSURE]: The skill accesses project-specific files such as PRDs, state JSON files, and project context files. However, it does not access sensitive system files (e.g., SSH keys, credentials) and contains no network operations to exfiltrate data.
- [COMMAND_EXECUTION]: The skill does not contain any shell command execution or subprocess spawning. Mentions of package managers (npm, bun) and frameworks are used for descriptive purposes in user prompts rather than execution.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external files which constitutes an ingestion surface.
- Ingestion points:
it_{iteration}_product-requirement-document.md,it_{iteration}_PRD.json,AGENTS.md, and.agents/PROJECT_CONTEXT.md. - Boundary markers: No specific delimiters or safety instructions are defined to separate ingested content from the generation prompt.
- Capability inventory: The skill is limited to reading local project files and writing markdown/JSON documentation within the project directory. It has no network, code execution, or administrative capabilities.
- Sanitization: No explicit sanitization or validation of the input file content is performed.
Audit Metadata