skills/immamdouhaboammar/antigravity-superpowers/agency-section-508-accessibility-specialist/Gen Agent Trust Hub
agency-section-508-accessibility-specialist
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data sources, including web applications, HTML source code, PDFs, and Office documents, to perform accessibility audits. This creates a surface for indirect prompt injection, where an attacker could embed malicious instructions within the content being audited to manipulate the agent's output or actions.
- Ingestion points: The skill instructions (Workflow Process Step 1 and 2) specify the ingestion of untrusted external content such as representative pages, task flows, and various document types.
- Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to ignore embedded instructions found within the audited data.
- Capability inventory: The skill involves 'remediating complex applications at the source' and rebuilding custom widgets, which implies the potential for the agent to generate or modify code based on findings from untrusted data.
- Sanitization: There are no instructions for sanitizing or filtering external content before processing or interpolation into responses.
Audit Metadata