sf-b2c-pwa-kit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from Salesforce's official developer portal and searches their GitHub repositories using the
WebFetchandWebSearchtools. These operations target well-known and trusted technology providers. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external documentation content at runtime.
- Ingestion points: Documentation content fetched from
developer.salesforce.comand GitHub search results as defined in the 'Before Writing Code' section ofSKILL.md. - Boundary markers: Not present; the agent is not specifically instructed to ignore instructions embedded in the external documentation.
- Capability inventory: The skill has access to
Bashfor command execution andWrite/Editfor file modifications. - Sanitization: Not present; the skill does not specify filtering or validation steps for the external content before it is processed by the agent.
Audit Metadata