pwa-offline-cache-contracts

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by instructing the agent to ingest and analyze external, potentially untrusted source code.
  • Ingestion points: The agent is guided to use search tools like rg (ripgrep) to process content from the project's src/ and app/ directories.
  • Boundary markers: The skill does not provide specific instructions to use delimiters or boundary warnings when reading external file content.
  • Capability inventory: The skill's primary function is local code auditing and architectural advice; it does not include dangerous capabilities such as persistent file writes or unauthorized network requests.
  • Sanitization: There are no specific sanitization or filtering requirements mentioned for the data retrieved from the source code searches before it is interpreted by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill includes reference links to documentation and implementation guidelines from well-known and trusted services, including MDN (Mozilla), Google's web.dev, Chrome for Developers, and official Vite documentation repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:59 PM
Security Audit — agent-trust-hub — pwa-offline-cache-contracts