spec-to-issue
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the
gh(GitHub CLI) tool to perform actions such asgh issue createandgh project item-add. These commands are standard for the skill's purpose of managing repository tasks. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including
requirement.md,design.md,tasks.md,CLAUDE.md, and.specs/.config.yml. This constitutes a vulnerability surface for indirect prompt injection. However, the risk is mitigated by a controlled extraction logic that identifies specific fields rather than performing a blind copy of the entire file. - [COMMAND_EXECUTION]: The skill contains a specific security instruction to avoid shell interpolation of untrusted content. It explicitly directs the agent to pass issue bodies via files or literal inputs to prevent the execution of malicious commands that might be embedded in the specification files.
- [DATA_EXPOSURE]: The skill accesses local project configuration files to resolve branch names, labels, and assignees. This metadata access is scoped to the repository and does not involve sensitive system files or credentials.
Audit Metadata