prd-start
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes shell commands using
gitand various forge CLIs (gh,glab,tea) to manage local branches and update issue assignments on remote platforms. This behavior is aligned with its primary purpose of setting up a development context. - [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface because it reads and processes Product Requirements Documents (PRDs) from the local file system to guide implementation tasks. • Ingestion points: Reads markdown files located in the
prds/directory. • Boundary markers: Absent; there are no instructions to ignore or delimit embedded commands within the PRD files. • Capability inventory: Includes the ability to execute git commands and install environment dependencies. • Sanitization: No evidence of sanitization or validation of the PRD content is provided before it influences agent actions.
Audit Metadata