google-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Google Analytics API, which includes user-controlled content like website page titles, referral sources, and campaign names. This creates an attack surface for indirect prompt injection if an attacker embeds instructions in these tracked fields that the agent then reads and executes during analysis.
- Ingestion points: Data is fetched via the BetaAnalyticsDataClient in
scripts/ga_client.pyand interpreted inscripts/analyze.py. - Boundary markers: The skill does not use specific delimiters or cautionary instructions to the agent to distinguish between analytics data and legitimate user instructions.
- Capability inventory: The skill can execute python scripts, access network resources (Google APIs), and write analysis reports to files. The agent is encouraged to translate data into strategic recommendations.
- Sanitization: No sanitization or safety-filtering is performed on the data returned from the API before it is presented to the agent for analysis.
Audit Metadata