The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation and checklists. It does not include any executable scripts, configuration files that trigger code execution, or dynamic context injection patterns.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for analyzing untrusted forensic artifacts, which creates a theoretical attack surface for indirect prompt injection if an agent parses malicious content within those artifacts.
Ingestion points: Forensic data sources including memory dumps (mem.dmp), PCAP network captures, Event Logs, and host artifacts like Prefetch and Shimcache (referenced in SKILL.md).
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings for the data being analyzed.
Capability inventory: There are no active scripts or tool permissions defined within the skill files themselves; it serves as a guide for using external tools like vol, tshark, and Autopsy.
Sanitization: No sanitization or filtering procedures for the forensic data are specified in the triage workflow.

digital-forensics