The Agent Skills Directory

[SAFE]: The skill is explicitly defined as a read-only analyzer in the Multi-Agent Reliability section. It performs purely analytical tasks and is prohibited from modifying files or performing network-based re-scans.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from external sources (aggregated web scan findings and Playwright snapshots). Ingestion points: Aggregated findings from web-accessibility-wizard and accessibility tree/keyboard data from playwright-scanner. Boundary markers: None detected within the prompt instructions to delimit untrusted data. Capability inventory: The skill is limited to data processing and generating structured output. It has no access to subprocesses, file-writing tools, or network operations. Sanitization: No explicit sanitization or validation of the input data is described.

cross-page-analyzer