repo-scan
Warn
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's installation instructions direct the user to fetch source code from an unverified GitHub repository (
https://github.com/haibindev/repo-scan.git). This involves downloading external content from a source that is not recognized as a trusted organization or well-known service. - [COMMAND_EXECUTION]: The installation process involves executing multiple shell commands (
git init,git remote add,git fetch,git checkout,cp -r) to download and deploy the skill's logic into the agent's environment. - [PROMPT_INJECTION]: The skill performs cross-stack scanning by reading the content of numerous files in a repository. This represents a surface for indirect prompt injection, as malicious instructions embedded in the scanned source code could potentially influence the agent's behavior during the audit process.
- Ingestion points: Source code files across various stacks (C++, Android, iOS, Web) read during the audit process described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded content are specified in the documentation.
- Capability inventory: The skill uses file-reading tools to classify files and identify libraries, and generates HTML reports.
- Sanitization: No evidence of sanitization or filtering of the scanned content is provided.
Audit Metadata