report-malicious-game-cheat-software
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data, such as repository metadata and README content, to detect malicious patterns. This creates an attack surface for indirect prompt injection if the processed content contains instructions targeting the agent.
- Ingestion points: The
detect_cheat_malware,analyze_repository_safety, andMalwareDetector.scan_readmefunctions all accept external text or metadata as input (e.g.,readme_content,repo_metadata). - Boundary markers: The skill does not implement explicit boundary markers or "ignore instructions" directives when processing the external content.
- Capability inventory: The skill utilizes regular expression matching (
re) for pattern detection and includes templates referencing network operations via therequestslibrary. - Sanitization: There is no evidence of sanitization, escaping, or filtering of the input strings before they are processed by the detection logic.
Audit Metadata