threat-intelligence-feed
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external, untrusted sources including public CVE databases, threat feeds, and GitHub Security Advisories. This creates an indirect prompt injection surface where malicious content within those feeds could attempt to influence the agent's behavior.
- Ingestion points: WebSearch results for NVD/CVE data, GitHub Security Advisory feeds, and local filesystem access to dependency manifest files (e.g., requirements.txt, package.json).
- Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore embedded instructions within the ingested threat data.
- Capability inventory: The agent has access to read project files and perform web searches to aggregate threat intelligence.
- Sanitization: There are no described mechanisms for sanitizing or validating the content retrieved from external sources before it is processed by the agent.
Audit Metadata