sf-b2c-pwa-kit

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides high-quality technical documentation and structural guidance for building headless storefronts with Salesforce's PWA Kit framework.- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and reference materials from official Salesforce developer portals and GitHub repositories. These are well-known, legitimate sources for the intended framework.- [COMMAND_EXECUTION]: Includes standard framework initialization and deployment commands, such as npx @salesforce/pwa-kit-create-app and npm run push. These are routine development actions within this ecosystem.- [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by instructing the agent to fetch and follow instructions from external websites and search results.
  • Ingestion points: External content is pulled into the agent's context via WebFetch and WebSearch tools as specified in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or warnings to distinguish fetched content from internal instructions or to ignore instructions embedded within the documentation.
  • Capability inventory: The skill allows the use of Bash, Write, and Edit tools, meaning instructions retrieved from the web could potentially influence file system modifications or command execution.
  • Sanitization: There is no mechanism described to sanitize or validate the content retrieved from external sources before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:10 AM
Security Audit — agent-trust-hub — sf-b2c-pwa-kit