write-product-spec
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external sources such as GitHub issues and Linear tickets, which introduces a surface for indirect prompt injection.
- Ingestion points: Context retrieved from Linear tickets and GitHub issues using CLI tools or MCP.
- Boundary markers: Absent; there are no specific instructions provided to the agent to distinguish between task-related metadata and potentially malicious instructions embedded in the ticket descriptions.
- Capability inventory: The skill can write to the local filesystem (
specs/directory) and utilize theghCLI tool. - Sanitization: No validation or sanitization steps are defined for the content pulled from these external platforms.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
ghCLI and Linear MCP tools for project management and ticket identification, which are legitimate developer tools used in a standard manner. - [SAFE]: The skill is primarily focused on creating structured Markdown documentation (
PRODUCT.md), which is a benign activity within a controlled development environment.
Audit Metadata