repomap
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the user to clone the tool's source code from the author's GitHub repository at
https://github.com/ariadoss/repomap.gitif it is not already present on the system. - [COMMAND_EXECUTION]: The skill executes a shell script (
scripts/run.sh) from the local installation directory to perform the repository mapping and generate aREPOMAP.mdfile. This script is part of the downloaded vendor package. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by generating a map of the codebase and instructing the agent to read it in future sessions. If a project contains malicious content (e.g., specially crafted file names or function names), this content could be included in the map and influence the agent's behavior when it reads the file.
- Ingestion points: Project file structure, classes, functions, and types (SKILL.md).
- Boundary markers: None specified for the content within
REPOMAP.md. - Capability inventory: File system read/write, shell command execution.
- Sanitization: No sanitization or filtering of the codebase content is described during the mapping process.
Audit Metadata