andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Address comprehensive GitHub review feedback

Browse Source 
- Add explicit security warnings about prompt injection and stop sequence pitfalls
- Enhance troubleshooting section with additional actionable guidance
- Improve default parameter behavior documentation
- Add cross-references for better navigation
- Clean up duplicate warnings from previous commits

Addresses feedback from joaomdmoura and mplachta reviews

Co-Authored-By: João <joao@crewai.com>
This commit is contained in:
Devin AI
2025-06-21 20:54:54 +00:00
parent 16110623b5
commit 80e2c34b7f
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/how-to/customize-prompts.mdx
View File

@@ -151,7 +151,7 @@ agent = Agent(
)
```
> **Note:** If `system_template`, `prompt_template`, or `response_template` are not provided, the default templates from `translations/en.json` are used.
> **Note:** If `system_template`, `prompt_template`, or `response_template` are not provided, the default templates from `translations/en.json` are used. The default system template includes role-playing instructions, tool descriptions (if applicable), and task formatting guidelines.
### Custom Stop Words via Response Template
@@ -311,6 +311,8 @@ NEXT STEPS: [Recommend next actions]""",
**Stop Words Not Effective**: Check that your `response_template` includes the desired stop sequence after the `{{ .Response }}` placeholder. See [Stop Words Configuration](#stop-words-configuration) for guidance.
**Template Injection Concerns**: Review the [Security Considerations](#security-considerations) section for guidance on preventing prompt injection attacks.
### Debugging Prompts
Enable verbose mode to see the actual prompts being sent to the LLM:
@@ -326,11 +328,13 @@ agent = Agent(
### Additional Troubleshooting Steps
#### Additional Troubleshooting Steps
- **Verify prompt payloads**: Use verbose mode to inspect the actual prompts sent to the LLM
- **Test stop word effects**: Carefully verify that stop sequences don't cause premature truncation
- **Check template syntax**: Ensure placeholders like `{{ .System }}` are correctly formatted
- **Validate security**: Review custom templates for potential injection vulnerabilities as described in [Security Considerations](#security-considerations)
- **Revert to defaults**: If custom templates aren't working, temporarily remove them to isolate the issue
- **Test incrementally**: Add one custom template at a time to identify which component is causing problems
- **Validate template parameters**: Ensure all required parameters (role, goal, backstory) are provided when using custom templates
For more troubleshooting guidance, see the sections above on [Best Practices](#best-practices) and [Security Considerations](#security-considerations).