search-console-connect

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data fetched from the Google Search Console API (queries, impressions, page titles). Maliciously crafted search queries or page metadata could potentially influence the agent's behavior if ingested without sanitization.
  • Ingestion points: Data is pulled from the Google Search Console API via scripts/pull.py and saved to .agents/gsc-data.json for analysis.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the GSC data.
  • Capability inventory: The skill is primarily focused on data analysis, formatting reports, and providing SEO recommendations; it does not exhibit dangerous capabilities like writing to system files or executing shell commands based on the ingested data.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the API.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill provides instructions for managing Google Cloud credentials, including accessing ~/.config/gcloud/application_default_credentials.json and creating .agents/search-console-credentials.json. While these involve sensitive information, the operations are standard for Google Cloud API integration and no unauthorized exfiltration patterns were observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 06:53 PM
Security Audit — agent-trust-hub — search-console-connect