repo-scan
Warn
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions direct the fetching of code from a community GitHub repository (https://github.com/haibindev/repo-scan.git). This source is not associated with the skill author or a verified organization.
- [REMOTE_CODE_EXECUTION]: By cloning the external repository and copying its contents into the agent's skill directory (~/.claude/skills/repo-scan), the skill enables the execution of unverified scripts or code provided by the third-party repository.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8). It is designed to read and classify arbitrary source code files. Malicious instructions embedded within these files (e.g., in comments or license files) could influence the agent's analysis or lead to deceptive reporting. Evidence:
- Ingestion points: Reads files across C++, Java, Swift, and Web stacks as defined in 'Analysis Depth Levels' (SKILL.md).
- Boundary markers: None provided to separate untrusted file content from analysis instructions.
- Capability inventory: Performs file classification, module scoring, and HTML report generation.
- Sanitization: No evidence of escaping or validation of ingested code content.
Audit Metadata