The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute well-known accessibility tools including @axe-core/cli, capture-website-cli, and playwright. These utilities are sourced from well-known official registries and are used according to their intended auditing purpose.
[COMMAND_EXECUTION]: To perform its tasks, the skill executes several shell commands to create directories (mkdir), run audits (npx), and process results (node -e). These operations are part of the documented automation workflow.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests and processes untrusted data from external URLs while having the capability to execute commands and modify local source code.
Ingestion points: Web content from user-provided URLs processed in Phase 9 (axe-core) and Phase 10 (Playwright).
Boundary markers: The skill does not specify markers or instructions to ignore potential commands embedded in the audited web content.
Capability inventory: Shell command execution via npx, file creation for reports, and direct source code modification in 'Interactive Fix Mode'.
Sanitization: No explicit sanitization or validation of the ingested external content is described.

web-accessibility-wizard