software-accessibility
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script
scripts/run_axe.shfetches the@axe-core/cliautomation tool from the public npm registry vianpx. This is a standard engineering practice for accessibility testing. - [COMMAND_EXECUTION]: The skill provides automated scripts (
scripts/run_axe.shandscripts/check_a11y_baseline.py) to execute accessibility scans and validate compliance claims. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data, specifically accessibility reports and user-provided JSON claims files.
- Ingestion points:
scripts/check_a11y_baseline.pyaccepts a user-provided JSON file via the--claimsargument;scripts/run_axe.shprocesses the output of theaxe-corescanner. - Boundary markers: None explicitly defined in the prompts, though the scripts expect structured JSON input.
- Capability inventory: The skill has the capability to execute shell commands (
npx) and read local files. - Sanitization:
scripts/check_a11y_baseline.pyimplements schema validation, type checking, and error handling for the ingested JSON data. - [SAFE]: All external references in
data/sources.jsonandSKILL.mdtarget official standards bodies (W3C), government regulators (FTC, DOJ), or well-known industry documentation sites (WebAIM, The A11Y Project).
Audit Metadata