timeline-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from multiple sources, creating a potential surface for indirect prompt injection.
- Ingestion points: Reads data from input/c2logs/, input/terminallogs/, input/notes/, and input/gw_oplog/ as referenced in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the input logs.
- Capability inventory: The skill orchestrates multiple sub-skills including timeline-cobaltstrike, timeline-mythic, and timeline-consolidator (as listed in SKILL.md) to parse and merge data.
- Sanitization: The provided instructions do not specify any sanitization or filtering logic for the input data.
Audit Metadata