responsive-image-contracts

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill contains shell probes using ripgrep (rg) to identify image tags and attributes within specific project directories (src/, app/, components/). These commands are standard for local static analysis and do not perform network operations or access sensitive system files.
  • [SAFE]: All external URLs referenced in the documentation point to trusted organizations or well-known technical documentation services, including MDN (Mozilla), web.dev (Google), W3C, and official GitHub repositories for established development tools like Markuplint and eslint-plugin-layout-shift.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and analyzing untrusted source code from a project. This creates a surface where malicious instructions could be embedded in the code being analyzed (e.g., in HTML comments).
  • Ingestion points: Project source files located in src/, app/, and components/.
  • Boundary markers: None explicitly defined; the agent processes the files as raw text for pattern matching.
  • Capability inventory: The skill utilizes ripgrep for local file searching; it does not contain code for file writing, network exfiltration, or privileged execution.
  • Sanitization: The skill relies on the agent's internal reasoning to interpret the search results rather than programmatic sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:59 PM
Security Audit — agent-trust-hub — responsive-image-contracts