threat-intelligence-feed
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources and local dependency files, which creates a vulnerability surface for indirect prompt injection. * Ingestion points: The skill reads external CVE feeds using WebSearch and scans local files such as requirements.txt and package.json via the filesystem tool. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the scanned data are defined in the skill instructions. * Capability inventory: The skill uses filesystem read access and network search capabilities to aggregate information. * Sanitization: There are no instructions for validating or sanitizing the ingested external content before it is included in reports or stored in memory.
Audit Metadata