timeline-mythic
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 parse Mythic C2 export files, which contain untrusted data such as operator commands and agent responses. This input could be leveraged by an attacker to influence the agent's behavior.
- Ingestion points: The skill reads JSON exports from the
input/c2logs/mythic/directory as described inSKILL.md. - Capability inventory: The skill is capable of processing structured data and writing to the local file system at
output/mythic_entries.json. - Boundary markers: The instructions do not include specific boundary markers or instructions for the agent to treat external log content as potentially malicious or non-authoritative.
- Sanitization: No explicit sanitization, filtering, or escaping is defined for the content extracted from log fields like
display_paramsorresponsesbefore they are interpolated into the output timeline.
Audit Metadata