The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted content from external websites.
Ingestion points: Content is ingested via read_page, read_console_messages, and read_network_requests tools as defined in SKILL.md.
Boundary markers: The instructions in SKILL.md do not specify boundary markers or directives to ignore instructions embedded within the processed web data.
Capability inventory: SKILL.md authorizes the use of navigate, form_input, and computer tools, enabling browser interaction and system-level actions.
Sanitization: There is no evidence of sanitization or filtering of website content before it is presented to the agent's context.

501-browser-qa-analyst