add-analytics-instrumentation

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted data from the user's codebase and feature descriptions to automate the creation of analytics tracking plans.
  • Ingestion points: Processes content from PR diffs, local files, directories, and natural language feature descriptions provided by the user.
  • Boundary markers: No specific delimiters or instructions are used to separate user-provided content from the agent's logic during the discovery phase.
  • Capability inventory: The skill executes file system reads and git commands, and orchestrates a pipeline that generates code-level instrumentation plans.
  • Sanitization: There is no evidence of sanitization or validation of the content read from files before it is processed by the event discovery logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 02:50 PM
Security Audit — agent-trust-hub — add-analytics-instrumentation