malware-game-cheat-detection
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a security-focused tool providing detection logic for game trainer malware. All code samples are benign heuristics for file and URL analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process untrusted repository data, including README files and directory listings.
- Ingestion points: Repository content, README files, and repository metadata provided by the user for scanning.
- Boundary markers: The implementation does not include specific delimiters or warnings to the agent to prevent obedience to instructions embedded within the analyzed content.
- Capability inventory: The skill uses file system operations (pathlib.Path.rglob) and regular expressions for detection. One script imports the subprocess module but does not execute any commands.
- Sanitization: Content is scanned for patterns but not sanitized or escaped to prevent injection during the evaluation process.
Audit Metadata