threat-intel-fusion
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and normalize data from various external and untrusted sources, which establishes a surface for indirect prompt injection attacks.
- Ingestion points: The workflow involves collecting information from OTX, MISP, abuse.ch, VirusTotal, Shodan, vendor blogs, and internal telemetry as specified in the fusion workflow in
SKILL.md. - Boundary markers: The instructions lack specific delimiting markers or guidance for the agent to ignore potentially malicious instructions embedded within the ingested threat intelligence.
- Capability inventory: According to the output contract in
SKILL.md, the agent is tasked with generating operational security artifacts, including Sigma, YARA, and Suricata rules, as well as SIEM-ready configurations. - Sanitization: There are no explicit requirements or steps defined for sanitizing, escaping, or validating the external content before it is processed or written to detection files.
- [NO_CODE]: The skill contains high-level operational guidelines and metadata but includes no scripts, binaries, or automated execution components.
Audit Metadata