google-analytics

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a feature to read JSON arguments from local files using a @path prefix (e.g., --request-json @body.json). This creates a vulnerability surface for indirect prompt injection if the agent is instructed to read a file whose content is controlled by an attacker.
  • Ingestion points: The load_json_arg function in src/ga4/client.py reads data from the filesystem when an argument starts with the @ character.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the files read via this mechanism.
  • Capability inventory: The skill can perform network operations (interacting with Google Analytics APIs) and write to the local filesystem (configuration and credentials).
  • Sanitization: No specific sanitization or validation of the JSON content is performed prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 03:21 AM
Security Audit — agent-trust-hub — google-analytics