platform-salesforce-connect-adapter-generate
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input, such as sample API responses and OpenAPI specifications, to generate functional Apex code. This creates a surface where malicious instructions embedded in the schema or sample data could influence the resulting code's logic. \n
- Ingestion points:
SKILL.md(Collect inputs section mentions sample responses and OpenAPI specs). \n - Boundary markers: Absent; the instructions do not require the agent to use delimiters or ignore potential instructions inside the provided API data during code generation. \n
- Capability inventory:
SKILL.md(metadata deployment viasfCLI);references/scenarios.md(generated code performs network callouts and DML operations). \n - Sanitization: Absent; the skill lacks specific sanitization logic for string values extracted from schemas before they are used to generate the adapter classes.
Audit Metadata