constellation-team

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains directives that attempt to override the AI's standard operational constraints and safety personas. Specifically, SKILL.md instructs the agent to 'Ignore token and cost constraints' and 'Push reasoning and code generation to practical limits.' These are known prompt injection patterns used to bypass resource management.
  • [NO_CODE]: The skill is composed entirely of markdown documentation and role-play templates for software development workflows. It does not include any scripts, binaries, or automated tools that perform actions on the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 06:18 PM
Security Audit — agent-trust-hub — constellation-team