license-compliance-scanner
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan external source code or documentation for license compliance. This creates a surface where an attacker could embed malicious instructions in the content being scanned to influence the agent's behavior.
- Ingestion points: The skill instructions imply reading user files or repository content to perform scanning operations.
- Capability inventory: The skill configuration scopes tool access to include Read, Write, Grep, and Bash(npm:*), which allows for file system modifications and execution of node-based tooling.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the data being scanned.
- Sanitization: There are no explicit sanitization or validation steps mentioned for handling content extracted during the license scan.
Audit Metadata