delivery-process-builder
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown instructions and templates. It does not contain any executable scripts, binaries, or commands that could compromise the host system or environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data, including client transcripts and business documents. It mitigates potential injection risks by enforcing a structured 12-block template, requiring verbatim data entry, and mandating a multi-round blind review process by subagents to verify output integrity before publication.
- [DATA_EXFILTRATION]: Although the workflow involves handling sensitive business information such as price lists and internal project post-mortems, these data points are used solely to populate internal templates and authorized deliverables. No unauthorized network requests or exfiltration patterns were identified.
- [EXTERNAL_DOWNLOADS]: The skill references several external tool dependencies (e.g.,
page-builder,proposal-generator). These are documented as internal extensions within established skill packs (gtm-skills,sales-engine-skills) and do not involve unverified third-party downloads.
Audit Metadata