aps-doc-staging
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and analyze untrusted data from a local codebase, specifically targeting .sql, .yml, and .dig files. \n
- Ingestion points: File content from user-provided directory paths, including SQL transformations and workflow definitions. \n
- Boundary markers: Lacks explicit delimiters or instructions to ignore potential commands embedded within the analyzed code files. \n
- Capability inventory: Requires file reading capabilities to perform analysis on SQL scripts, configuration files, and workflow definitions. \n
- Sanitization: No evidence of content validation or sanitization is defined for the data extracted from the codebase before it is incorporated into the documentation output.
Audit Metadata