superpowers-tdd

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of natural language instructions in a Markdown file. No scripts, configuration files, or binaries are included.
  • [PROMPT_INJECTION] (SAFE): Evaluation of indirect prompt injection surface.
  • Ingestion points: Workspace source code and test files processed by the agent.
  • Boundary markers: Not specified in the skill body.
  • Capability inventory: Directs the agent to execute shell commands for running test suites and linters.
  • Sanitization: No sanitization or validation of the ingested code content is specified.
  • Context: The risk is inherent to the development task and not introduced by malicious instructions within the skill; the TDD process itself is standard and safe.
  • [SAFE] (SAFE): No malicious patterns such as direct prompt injection, data exfiltration, or obfuscation were detected. The instructions follow software engineering best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM