The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data including memory dumps, PCAP files, and Windows host artifacts.
Ingestion points: Processes forensic artifacts like mem.dmp and network streams as described in SKILL.md.
Boundary markers: There are no instructions or delimiters provided to separate the parsed artifact content from the agent's internal instructions.
Capability inventory: The skill uses forensic tools such as vol (Volatility) and tshark to interpret binary data.
Sanitization: The instructions do not include steps to sanitize or validate output from forensic tools before the agent processes it.

digital-forensics