google-agents-cli-observability

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill describes implementing a feedback mechanism in references/feedback-mechanism.md that ingests arbitrary user text.
  • Ingestion Point: Untrusted user input enters the system through the /feedback FastAPI endpoint into the Feedback model's text field.
  • Capability Inventory: Ingested data is stored in BigQuery and Cloud Logging, where it is intended to be used for conversational analytics and LLM-as-judge evaluations.
  • Boundary Markers: There are no specific instructions or delimiters provided to prevent the agent from interpreting instructions embedded within the feedback text during subsequent analysis.
  • Sanitization: While the skill advises on PII redaction, it does not provide methods for sanitizing the input against adversarial prompt instructions.
  • Command Execution: The skill involves the use of agents-cli, bq, and gsutil for infrastructure management and data verification. These are part of the skill's primary functionality for managing Google Cloud resources and do not represent unexpected behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:33 AM
Security Audit — agent-trust-hub — google-agents-cli-observability