seo-google

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, such as user-generated YouTube comments and the content of arbitrary web pages analyzed via Google's Natural Language and PageSpeed APIs. This content is presented to the agent, creating a surface for indirect prompt injection where malicious instructions embedded in external data could attempt to influence agent behavior. \n
  • Ingestion points: YouTube video comments, NLP entity extraction results from arbitrary text/URLs, and site performance data from user-provided URLs. \n
  • Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions to separate external data from the agent's core instructions. \n
  • Capability inventory: The skill environment facilitates network operations via Python scripts to various Google APIs and local file system writes for caching and reporting. \n
  • Sanitization: No explicit sanitization or validation of the ingested external content is described in the skill instructions. \n- [COMMAND_EXECUTION]: The skill facilitates the execution of local Python scripts (e.g., google_auth.py, pagespeed_check.py, gsc_query.py) that perform authorized network requests and data processing tasks. \n- [EXTERNAL_DOWNLOADS]: The documentation references the installation of official Google client libraries, such as the google-ads Python package. These are well-known dependencies from a trusted vendor required for the skill's primary functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 07:40 AM
Security Audit — agent-trust-hub — seo-google