map-codebase
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the Bash tool to execute git and gh (GitHub CLI) commands for repository state inspection, drift calculation, and GitHub issue management (create, edit, comment).- [EXTERNAL_DOWNLOADS]: References the official GitHub CLI website (https://cli.github.com) for users to install the prerequisite tool if it is not present on the system.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface by ingesting and processing untrusted data from the repository being mapped.
- Ingestion points: The skill reads arbitrary codebase files using Read, Glob, and Grep tools in SKILL.md and through sub-agents dispatched in references/mapper-dispatch.md.
- Boundary markers: While instructions tell sub-agents to return specific sections, there are no explicit boundary markers or isolation protocols to prevent untrusted file content from influencing the agent's logic or output.
- Capability inventory: The skill possesses capabilities to execute Bash commands (scoped to git and gh), spawn sub-agents (Agent tool), and write to GitHub issues.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the repository content before it is processed by mappers or appended to the GitHub issue body.
Audit Metadata