google-search-console
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage from the NPM registry to interact with the Membrane platform. - [COMMAND_EXECUTION]: The skill uses shell commands through the
membraneCLI to manage user authentication, connection state, and API requests (e.g.,membrane login,membrane action run). - [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Google Search Console API, creating a surface for potential indirect prompt injection from external site data.
- Ingestion points: Performance reports (queries, pages), sitemap data, and URL inspection results fetched via CLI commands described in
SKILL.md. - Boundary markers: Absent; no specific delimiters or warnings for the agent to ignore instructions within the search data are defined.
- Capability inventory: Shell command execution via
membraneCLI for reading and writing site configuration (e.g.,add-site,delete-site,submit-sitemap) as documented inSKILL.md. - Sanitization: Absent; no evidence of data sanitization or input validation for external content was found in the skill instructions.
Audit Metadata