simmer-setup

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill is designed to inspect workspace files, including potentially sensitive configuration files like .env, to identify parameters and variables that can be refined during the optimization process.
  • [COMMAND_EXECUTION]: The skill identifies and prepares local shell commands (e.g., evaluate.sh, validate.sh) found within a workspace to be included in a setup brief for subsequent execution by an orchestrator.
  • [PROMPT_INJECTION]: The skill processes untrusted data from local file contents and directory structures to infer evaluation logic and contracts, creating an indirect prompt injection surface.
  • Ingestion points: Files and directory structures read during the 'Identify and Inspect' phase in SKILL.md.
  • Boundary markers: None identified in the prompt interpolation logic.
  • Capability inventory: The skill identifies and formats shell commands for external script execution to be used in the 'Setup Brief'.
  • Sanitization: No specific sanitization or escaping of external content is mentioned before it is included in the brief.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 01:24 AM