product-tracking-audit-current-tracking
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by systematically scanning the user's codebase to identify tracking patterns and SDK implementations. This ingestion creates a surface where malicious instructions embedded in the project's source code could influence the agent's behavior during the audit process.
- Ingestion points: Project files are scanned using the
rgtool and directly read by the agent to extract event names, properties, and context (documented inSKILL.md). - Capability inventory: The skill has the capability to execute shell commands (
rg) and write multiple files to the local.telemetry/directory. - Boundary markers: The instructions do not specify the use of delimiters or provide the agent with explicit warnings to ignore instructions found within the scanned code content.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the content ingested from the codebase before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill utilizes the
rg(ripgrep) command-line utility to search for specific analytics patterns (e.g.,analytics.track,posthog.capture) across the project's JavaScript and TypeScript files.
Audit Metadata