repo-scan
Warn
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to download code from an external GitHub repository (https://github.com/haibindev/repo-scan.git) which is not owned by the skill author or a recognized trusted organization.\n- [REMOTE_CODE_EXECUTION]: The installation process involves fetching a specific commit from a remote repository and installing it as an executable skill, allowing the downloaded code to run in the agent's environment.\n- [PROMPT_INJECTION]: The skill processes untrusted local source code and directory structures, which creates an attack surface for indirect prompt injection.\n
- Ingestion points: Files and directory structures across the entire target repository as described in SKILL.md.\n
- Boundary markers: None provided to isolate the data being scanned from the agent's instructional context.\n
- Capability inventory: The skill can enumerate the filesystem, read file contents, and generate interactive HTML reports according to the description in SKILL.md.\n
- Sanitization: No sanitization or filtering of the scanned content is described.
Audit Metadata