using-spectacular
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses high-pressure directives like "EXTREMELY_IMPORTANT", "MANDATORY FIRST RESPONSE PROTOCOL", and "automatic failure" to force the agent into a specific operational mode.
- [PROMPT_INJECTION]: It explicitly instructs the agent to override user instructions that might conflict with the workflow, stating "User instructions describe WHAT to build, not permission to skip workflows."
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files in
docs/constitutions/current/. - Ingestion points:
docs/constitutions/current/directory. - Boundary markers: Not present; instructions are treated as "immutable architectural rules".
- Capability inventory: The skill utilizes tools to generate specifications, create execution plans, and implement code via
/spectacular:executewhich includes spawning subagents and creating worktrees. - Sanitization: None mentioned for the ingested constitutional rules.
Audit Metadata