agent-squad-python
Use when building or modifying a Python app that uses the agent-squad Python package — async multi-agent orchestration for Python 3.11+: orchestrator, agents (BedrockLLMAgent, AnthropicAgent, OpenAIAgent, SupervisorAgent, GroundedAgent, ChainAgent, and more), classifier routing (Bedrock, Anthropic, OpenAI), storage (in-memory, DynamoDB, SQL/Turso), retrievers (Amazon KB, Dakera), tools (AgentTools, MCPToolProvider), and custom implementations.
72
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In `src/agent_squad/agents/anthropic_agent.py`, `AnthropicAgent._prepare_system_prompt` calls `self.retriever.retrieve_and_combine_results(input_text)` and appends the resulting retrieved context (which may include outsider-authored text) into the system prompt that is then sent to `self.client.messages.create(**input_data)`, so the LLM ingests untrusted retrieved free text at runtime.
- Repository
- 2FastLabs/agent-squad
- Path
python/SKILL.md
- Commit
31eccfe
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.