skills/eyadsibai/ltk/dspy-prompting/Gen Agent Trust Hub

dspy-prompting

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the dspy Python library from the official package registry. This is a standard dependency for the tool developed by Stanford NLP.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes pipelines that ingest and process external data, creating an indirect injection surface.
  • Ingestion points: Code snippets in SKILL.md (e.g., QA, MathProblem, ExtractPerson) process user-provided question, problem, and text fields.
  • Boundary markers: The examples do not include explicit delimiter-based isolation or specific instructions for the model to ignore embedded commands within the user-provided inputs.
  • Capability inventory: The code snippets demonstrate network capabilities for communicating with external LLM providers (Anthropic, OpenAI) and local instances (Ollama).
  • Sanitization: The provided examples do not demonstrate input validation or content filtering before the data is processed by the language model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:08 PM