repo-scan
Warn
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides installation steps that download code from an external GitHub repository (
github.com/haibindev/repo-scan.git). This source is not verified or associated with the skill's author context. - [PROMPT_INJECTION]: The skill processes untrusted external data during its audit process, which creates a surface for indirect prompt injection. Malicious instructions hidden within scanned source code, headers, or license files could potentially influence the agent's analysis or the resulting reports.
- Ingestion points: The skill reads and analyzes directory names, file headers, license files, and version markers from arbitrary repositories.
- Boundary markers: There are no specified delimiters or instructions to ignore content within the analyzed files to prevent obedience to embedded instructions.
- Capability inventory: The skill classifies files, detects libraries, and generates multi-level verdicts and interactive HTML reports.
- Sanitization: The skill description does not mention any sanitization or validation of the content extracted from audited files before it is processed for report generation.
Audit Metadata