pipeline-health
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill does not contain any executable scripts (Python, JavaScript, shell) or external dependencies. It consists entirely of markdown instructions and evaluation configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (CRM deal records) which could be used as an ingestion vector.
- Ingestion points: Data ingested into the 'Zombie Deal Purge Register' and the 'Pipeline Health Audit Report' (e.g., Deal Name, Account Executive).
- Boundary markers: The templates do not use specific delimiters or instructions to ignore embedded prompts in the ingested data.
- Capability inventory: The skill does not define any capabilities (such as shell execution, file system writes, or network access) that an injected prompt could exploit.
- Sanitization: No validation or sanitization of input data is specified in the audit process.
Audit Metadata