indexing-issue-auditor
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from local directories, public URLs, and external CSV reports, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests data from local file systems (e.g.,
sitemap.xml,robots.txt) and external CSV exports as defined in the 'Input Types' section ofSKILL.md. - Boundary markers: Instructions lack clear boundary delimiters or explicit 'ignore embedded instructions' warnings for the data being processed during the audit phases.
- Capability inventory: The skill utilizes platform tools (
claude,cursor,gemini) which typically possess file-system access and terminal capabilities, increasing the potential impact of an injection. - Sanitization: There is no specified logic for sanitizing or validating external content before it is processed by the agent.
Audit Metadata