indexing-issue-auditor
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from multiple external sources.
- Ingestion points: Untrusted data enters the agent context through the analysis of local directory paths, CSV files (GSC reports), and live public domain URLs.
- Boundary markers: The instructions do not specify the use of delimiters or provide directives for the agent to ignore potentially malicious instructions embedded within the data being audited.
- Capability inventory: The skill utilizes tools such as Claude and Cursor, which typically possess capabilities for file system interaction and potentially code execution in the development environment.
- Sanitization: There are no defined procedures for sanitizing, validating, or escaping the content retrieved from external URLs or data files before it is processed.
Audit Metadata