nest-boot-skill-maintainer
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub PR comments, issue descriptions, and repository files. This creates a surface area for indirect prompt injection where instructions embedded in external content could attempt to influence agent behavior.
- Ingestion points: Reads external text from PR comments, issue threads, and target source files using the
ghCLI. - Boundary markers: The instructions do not define specific delimiters or isolation techniques for processing untrusted external text.
- Capability inventory: Accesses the file system, manages git branches, and performs authenticated GitHub operations (issue/PR creation) via the
ghCLI. - Sanitization: The skill emphasizes manual data de-identification before submission but does not implement automated sanitization for incoming external data.
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) for repository operations such as listing issues, checking PR status, and creating contributions. These are standard developer operations performed on a well-known service (GitHub) and are consistent with the skill's primary purpose.
Audit Metadata