The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external artifacts, including disk images, memory dumps, network captures (PCAP), and various steganographic files, which could potentially contain malicious instructions.
Ingestion points: Forensic artifact processing workflows detailed throughout the reference files, such as references/network-triage.md and references/advanced-disk-and-memory.md.
Boundary markers: The instructions do not define explicit boundary markers or instructions to ignore embedded content when parsing these untrusted files.
Capability inventory: The skill provides workflows involving significant system capabilities, including file system mounting (sudo mount), direct block level access (dd), network analysis (tshark), and numerous specialized forensics tools.
Sanitization: There is no mention of automated sanitization or filtering of the content within the artifacts being analyzed.
[COMMAND_EXECUTION]: The skill provides extensive workflows for executing forensics tools and shell commands (e.g., volatility3, sleuth-kit, binwalk, tshark). These are legitimate within the context of CTF forensics analysis and professional offensive methodology.
[EXTERNAL_DOWNLOADS]: The reference material provides instructions for downloading and installing established security tools and libraries from well-known repositories (e.g., John the Ripper, FemtoZip, bkcrack) for forensic recovery tasks.

forensics-ctf