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