home-designer-crack-detection
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external software repositories, specifically their README text, metadata, and file lists. This creates an attack surface where a malicious repository could include hidden instructions intended to override the agent's analysis or behavior.
- Ingestion points: The skill triggers on commands to "analyze this home design software repository" and "scan for crack or keygen distribution", which involves reading external content provided in the agent's context (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings when processing the contents of external repositories.
- Capability inventory: The skill utilizes text analysis and regular expression scanning to identify threats. It does not perform high-risk network or file system operations itself.
- Sanitization: While the skill scans for malicious keywords using regex, it does not implement sanitization or escaping of the ingested text to prevent it from being interpreted as instructions by the underlying model.
Audit Metadata