The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection because it ingests data from external Zscaler resources (firewall rules, URL filtering, DLP dictionaries).
Ingestion points: Data enters through tools like list_firewall_rules, get_url_filtering_rule, list_dlp_dictionaries, and list_locations in SKILL.md.
Boundary markers: There are no specified boundary markers or instructions to ignore embedded commands in the processed data.
Capability inventory: The skill possesses significant write capabilities, including create_firewall_rule, update_firewall_rule, and delete_firewall_rule defined in SKILL.md.
Sanitization: No sanitization or validation of the retrieved external content is described.

zscaler-zia