skills/aaaaqwq/agi-super-team/ast-cto/Gen Agent Trust Hub

ast-cto

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest business objectives, architecture constraints, and user requirements, which it uses to orchestrate a wide range of technical sub-skills.
  • Ingestion points: Processes high-level business goals, system boundaries, and user journey descriptions provided in the task context (SKILL.md).
  • Boundary markers: The instructions include clear responsibility guidelines and user collaboration boundaries to prevent data leakage, though the skill does not use technical delimiters (e.g., XML tags) for input data.
  • Capability inventory: The skill has authority to delegate tasks to 20 specialized tools, including infrastructure management (kubernetes-deployment), observability (sentry-automation), and secret management (provider-key-manager).
  • Sanitization: The instructions explicitly mandate that sensitive data, credentials, and personal profiles must not be written to long-term memory or shared across sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 12:34 PM