rdd-decide

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface by processing content from external project files and the user's codebase.
  • Ingestion points: The skill reads data from ./docs/essays/, ./docs/product-discovery.md, ./docs/decisions/, and the general project codebase as part of its audit and decision steps.
  • Boundary markers: No delimiters or 'ignore' instructions are defined to separate the ingested artifact data from the agent's core instructions.
  • Capability inventory: The skill uses tools for file system manipulation (Read, Write, Edit, Grep, Glob) and network access (WebSearch, WebFetch).
  • Sanitization: There is no instruction to sanitize, validate, or escape ingested content before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:12 AM