search-console
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow an external workflow file as its active instruction set.
- Ingestion points: The skill directs the agent to read
../../analytics/search-console/WORKFLOW.mdand treat it as the active workflow inSKILL.md. - Boundary markers: There are no markers, delimiters, or explicit instructions to ignore potentially malicious embedded commands within the external file.
- Capability inventory: The skill enables the agent to interact with Google Search Console, including performing URL inspections and submitting or removing sitemaps.
- Sanitization: The skill lacks any mechanism to sanitize or validate the content of the external markdown file before following its instructions.
Audit Metadata