The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display external data such as security events, threat intelligence, and sandbox reports, which could potentially contain malicious instructions embedded by external actors.
Ingestion points: get_threat_intelligence, list_security_events, list_anomalies, and get_sandbox_report tools defined in SKILL.md.
Boundary markers: The skill manifest does not define delimiters or explicit instructions for the agent to ignore embedded commands within the retrieved threat data.
Capability inventory: The tools listed are primarily focused on information retrieval (GET/LIST operations); there are no visible tools for file-system writing, network transmission, or system command execution defined in this manifest.
Sanitization: There are no instructions for sanitizing or filtering retrieved content before it is presented to the agent.
[NO_CODE]: The provided skill consists solely of a markdown definition file (SKILL.md) and does not include any executable scripts, binaries, or automated installation commands.

zscaler-insights