The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (binary samples) which can contain adversarial instructions.
Ingestion points: Untrusted data enters the agent's context through the output of static analysis tools, specifically strings -a sample.exe, rabin2 -i sample.exe, and diec sample.exe as described in Phase 2.
Boundary markers: The instructions do not define clear delimiters or provide the agent with guidance to disregard instructions embedded within the strings or metadata of the analyzed files.
Capability inventory: The skill utilizes several subprocess/shell capabilities including file, sha256sum, strings, diec, exeinfope, rabin2, and dumpbin.
Sanitization: There is no evidence of sanitization, filtering, or escaping of the output generated by the analysis tools before it is processed by the agent.

malware-analyst