The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs during the audit process, which creates a surface for indirect prompt injection attacks.
Ingestion points: Content from user-provided URLs is processed by site_crawler.py and scripts/seo_lint.py as described in the workflow.
Boundary markers: The instructions do not specify any delimiters or safety guidelines to differentiate between target website content and the agent's internal instruction set.
Capability inventory: The skill possesses capabilities to write files to the local system and execute localized Python scripts.
Sanitization: There is no evidence of sanitization or validation protocols for the data retrieved from external sources before it is interpreted by the agent or included in markdown reports.
[COMMAND_EXECUTION]: The skill uses localized Python scripts to perform analysis and publishing tasks.
Evidence: The workflow involves executing python scripts/seo_lint.py and python scripts/report_publish.py with arguments such as URLs and filenames. These represent shell command execution capabilities using local scripts.

accessibility-audit