easy-prd
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to perform standard file operations such as saving the generated PRD to a user-specified path (--out). This is consistent with its stated purpose of document generation. - [SAFE]: The static analysis hint regarding prompt injection in
templates/prd-example.mdis a false positive. The file contains a requirements document for an AI Support Agent which correctly includes requirements about preventing prompt injection (FR-003) and mentions common injection patterns as test cases for the agent's safety filters. This is a best-practice documentation for the system being described, not an attempt to inject instructions into the analyzer or the host agent. - [SAFE]: The skill requests access to standard tools (
Read,Write,Edit,Bash,AskUserQuestion) which are appropriate for its core functionality of interacting with the user and saving files to the local workspace. - [SAFE]: All external references (such as the author's GitHub and website) and installation instructions point to the vendor's own infrastructure ('instantX-research') and represent legitimate resources for the skill's distribution and documentation.
Audit Metadata