pipeline-health-analyzer-skill

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data sources, creating a potential surface for indirect prompt injection where instructions could be embedded in the pipeline data. Ingestion points: SKILL.md (Quick Start and Workflow) explicitly requests pipeline exports in CSV format or CRM access. Boundary markers: No instructions are provided to establish boundaries for external data or to ignore embedded commands. Capability inventory: The skill consists purely of instructions and lacks any executable tools, scripts, or network capabilities, limiting the potential impact of an injection. Sanitization: No data validation, filtering, or sanitization steps are defined for the ingested data.
  • [NO_CODE]: The skill does not contain any Python code, Node.js scripts, or binaries. It is composed entirely of markdown instructions and metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 06:50 PM