pipeline-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external sources (CRM, GA4, Semrush, campaign-feedback), creating a surface for indirect prompt injection.\n
- Ingestion points: The skill explicitly pulls from various external data sources listed in the inputs section of SKILL.md.\n
- Boundary markers: No delimiters or isolation instructions are specified to separate untrusted data from the agent's instructions.\n
- Capability inventory: The skill describes workflows for summarizing and reporting on potentially attacker-influenced data.\n
- Sanitization: No input validation, filtering, or sanitization logic is described or implemented.\n- [NO_CODE]: The analyzed file contains only markdown documentation and metadata; it does not include executable scripts, shell commands, or tool definitions.
Audit Metadata