advanced-persistent-threat
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown documentation. It does not include any scripts, binaries, or automated tools, posing no direct execution risk.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting untrusted external data. Ingestion points: CTI reports, incident timelines, and telemetry summaries (SKILL.md, references/apt_scope_and_definitions.md). Boundary markers: No specific delimiters are defined. Capability inventory: The skill contains no executable scripts, tool configurations, or command execution capabilities. Sanitization: No sanitization of external content is specified. Due to the lack of capabilities, this represents a non-exploitable surface.
- [DATA_EXPOSURE]: Although the skill guides the analysis of sensitive security logs and infrastructure, it does not contain hardcoded secrets, nor does it include instructions for data exfiltration or unauthorized access.
Audit Metadata