gtm-analytics-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans and processes various frontend component files and local context files. Malicious instructions hidden within these files (e.g., in code comments or tag attributes) could influence the agent's behavior or output.
- Ingestion points: Scans source files in app/, pages/, components/, and src/ directories, as well as package.json and gtm-context.md.
- Boundary markers: Absent; no specific instructions are provided to the agent to ignore or delimit embedded instructions within the scanned data.
- Capability inventory: The skill is capable of reading project files and writing findings to audit-report.json and gtm-context.md.
- Sanitization: No sanitization or validation steps are defined for the data extracted from the codebase before it is processed by the agent.
Audit Metadata