dev-plan
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data from GitHub issues (titles and bodies) using the
gh issue viewcommand. This content is used to generate prompts for subsequent development tasks, creating an indirect prompt injection surface.\n - Ingestion points: GitHub issue content fetched during Step 2 of the workflow (SKILL.md).\n
- Boundary markers: Absent. The generated markdown prompts do not use specific delimiters or instructions to ignore potential commands within the issue text.\n
- Capability inventory: The generated prompts (references/prompt-template.md) instruct the agent to use tools like
/gtr-workflow,/e2e-test, and/pull-requestfor file creation and command execution.\n - Sanitization: No sanitization or filtering of the issue content is mentioned or implemented before it is interpolated into the prompt template (SKILL.md).\n- [COMMAND_EXECUTION]: The skill instructions require the use of the
ghCLI to interact with GitHub issues.\n- [NO_CODE]: The skill is defined entirely through markdown files (SKILL.md and references) and does not include executable code scripts.
Audit Metadata