The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of PST/OST files. These files contain emails, headers, and attachments originating from external senders, which can include malicious instructions targeting the AI agent's logic.
Ingestion points: The script scripts/agent.py and the Python example in SKILL.md process user-provided mailbox files via pypff.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the extraction logic.
Capability inventory: The skill possesses file system write capabilities (saving attachments and reports) and provides a series of shell commands for external forensic tools.
Sanitization: While scripts/agent.py performs basic filename sanitization for extracted attachments, it does not sanitize or filter the text content of emails (subjects, bodies, headers) which are extracted verbatim into reports.
[COMMAND_EXECUTION]: The skill provides numerous shell commands for third-party forensic tools such as pffexport, pffinfo, and readpst. The agent is expected to execute these commands on the host system to perform the analysis.

analyzing-outlook-pst-for-email-forensics