api-analysis-sitecore-and-bff
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external data from Sitecore and BFF API specification files (
./.SC_API_SPEC/sitecore-api.jsonand./.BFF_API_SPEC/{operationId}.json). While the skill is intended to extract field names and scenarios into markdown tables, the lack of explicit boundary markers or sanitization logic when processing these untrusted inputs presents a surface for indirect prompt injection. A malicious specification file could contain instructions designed to influence the agent's output or reasoning. - Ingestion points:
SKILL.mdidentifies Sitecore API JSON and BFF API specs as input files to be read and analyzed. - Boundary markers: The instructions do not define delimiters or warnings to treat the content of the spec files as untrusted data.
- Capability inventory: The skill is restricted to logic checks and report generation; it lacks network access, file-write (beyond specified plans), and shell execution capabilities.
- Sanitization: The skill does not perform sanitization or validation of the content within the specification files beyond checking for the presence of fields.
Audit Metadata