b2c-cip
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is designed to ingest and process data from external SQL queries and reports (CIP/CCAC data).
- Ingestion points: Data enters the agent context through the output of
b2c cip queryandb2c cip reportcommands executed in the shell. - Boundary markers: The instructions do not specify the use of clear delimiters or 'ignore embedded instructions' warnings for the data returned from these queries.
- Capability inventory: The skill utilizes the
b2cCLI for querying databases, reporting metrics, and describing schemas, which includes the ability to execute raw SQL. - Sanitization: No explicit sanitization or filtering of the database output is described in the prompt instructions before the agent processes the results.
- Context: This risk is inherent to the primary purpose of the skill (data analytics) and is documented here as an architectural observation rather than a malicious finding.
Audit Metadata