← Legacy view v2 (rp.*)

wenyuchiou/awesome-agentic-ai-zh

https://github.com/WenyuChiou/awesome-agentic-ai-zh · lang: python · LOC: · source: both

Quality
76.4
Grade B+
Security
79.4
Findings
10
0 critical · 3 high
Status
completed
May 16, 2026 04:24
info: 4 high: 3 medium: 3
Top rules by occurrence
RuleSeverityCount
SEC020 Secret Printed to Logs high 4
SEC017 Unbounded Input to LLM/External API medium 3
SEC016 LLM Prompt Injection — User Input in AI Prompt high 2
SEC002 Hardcoded API Key critical 1
First 10 findings (severity-sorted)
high SEC016 LLM Prompt Injection — User Input in AI Prompt
examples/stage-4/01-same-agent-two-frameworks/starter_crewai.py:44 · conf 0.90 
[SEC016] LLM Prompt Injection — User Input in AI Prompt: User-supplied text is interpolated directly into an AI/LLM prompt (e.g. OpenAI, Anthropic, or local model). This is the AI equivalent of SQL i…
high SEC016 LLM Prompt Injection — User Input in AI Prompt
examples/stage-4/02-multi-agent-roles/starter.py:56 · conf 0.90 
[SEC016] LLM Prompt Injection — User Input in AI Prompt: User-supplied text is interpolated directly into an AI/LLM prompt (e.g. OpenAI, Anthropic, or local model). This is the AI equivalent of SQL i…
high SEC020 Secret Printed to Logs
examples/stage-1/04-cross-provider/starter.py:124 · conf 0.85 
[SEC020] Secret Printed to Logs: Debug or diagnostic code appears to print a credential-bearing value. This is a frequent AI-assisted coding failure: the helper exposes the exact value needed for tro…
medium SEC017 Unbounded Input to LLM/External API
examples/stage-4/01-same-agent-two-frameworks/starter_crewai.py:44 · conf 0.80 
[SEC017] Unbounded Input to LLM/External API: User input is passed to an LLM or external AI API (OpenAI, Anthropic, etc.) without any visible length or size validation. This creates two risks: (1) Co…
medium SEC017 Unbounded Input to LLM/External API
examples/stage-4/02-multi-agent-roles/starter.py:56 · conf 0.80 
[SEC017] Unbounded Input to LLM/External API: User input is passed to an LLM or external AI API (OpenAI, Anthropic, etc.) without any visible length or size validation. This creates two risks: (1) Co…
medium SEC017 Unbounded Input to LLM/External API
examples/stage-4/03-graph-workflow/starter_anthropic.py:29 · conf 0.80 
[SEC017] Unbounded Input to LLM/External API: User input is passed to an LLM or external AI API (OpenAI, Anthropic, etc.) without any visible length or size validation. This creates two risks: (1) Co…
info SEC002 Hardcoded API Key
examples/stage-1/05-error-handling/starter_anthropic.py:70 · conf 0.15 
[SEC002] Hardcoded API Key: Hardcoded API key found in source code.
info SEC020 Secret Printed to Logs
· conf 0.20 
[SEC020] Secret Printed to Logs (and 4 more): Same pattern found in 4 additional files. Review if needed.
info SEC020 Secret Printed to Logs
examples/stage-1/05-error-handling/starter_anthropic.py:112 · conf 0.15 
[SEC020] Secret Printed to Logs: Debug or diagnostic code appears to print a credential-bearing value. This is a frequent AI-assisted coding failure: the helper exposes the exact value needed for tro…
info SEC020 Secret Printed to Logs
examples/stage-1/05-error-handling/starter.py:126 · conf 0.15 
[SEC020] Secret Printed to Logs: Debug or diagnostic code appears to print a credential-bearing value. This is a frequent AI-assisted coding failure: the helper exposes the exact value needed for tro…

Reading from rp.scan + rp.finding + rp.rule (unified schema, R78 series). Legacy data path unchanged. Compare with /scan/fdd7314a-a138-4060-86e1-49caaf4d6fdc/.