skills/zaks-io/skills/ziw-to-issues/Gen Agent Trust Hub

ziw-to-issues

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources such as spec documents, PRDs, and existing tracker tickets to generate implementation issues.
  • Ingestion points: External planning documents and existing issue tracker tickets specified in SKILL.md (Inputs section).
  • Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the processed data to prevent the agent from obeying instructions inside the documents.
  • Capability inventory: The skill has the capability to read local configuration files (docs/agents/workflow/config.md) and create or modify tickets in an external issue tracker.
  • Sanitization: There are no instructions for sanitizing or validating the content of input documents before it is interpolated into the generated ticket bodies, creating a surface for prompt injection from external contributors.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 05:33 PM
Security Audit — agent-trust-hub — ziw-to-issues