Add interprocedural taint checks for Bandit injection sinks
Track user input through variables and calls so Bandit flags injection sinks beyond string literals.
bandit-interprocedural-taint-checks
Normalized profile
What this task asks for
Track user input through variables and calls so Bandit flags injection sinks beyond string literals. Track input taint from Flask request data, `sys.argv`, `input()`, and `os.environ` into security-sensitive sinks. Propagate taint through string construction, calls, multi-hop assignments, nested functions, and import aliases. Treat parameterized query values, numeric conversion, path basenames, shell quoting, and HTML escaping as safe. Add B620 through B624 checks for SQL injection, shell injection, path traversal, SSRF, and XSS sinks. Report every new plugin finding with HIGH severity and MEDIUM confidence.
Intent
- feature implementation
- security remediation
- data transformation
Work surfaces
- query layer
- serialization
Technology
- Bandit
- SQL
Expected artifacts
- repository patch
What makes it difficult
- security-sensitive or adversarial behavior
- specialized algorithmic or domain reasoning
Published evidence
Model × harness outcomes
Counts are tied to these exact configurations. Harnesses are not treated as equivalent across benchmarks.
- Models
- 13
- Configurations
- 41
- Trials
- 164
Showing 41 of 41 configurations
| Model | Harness | Effort | Result | Passes |
|---|---|---|---|---|
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | low | Mixed | 3/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | medium | Mixed | 2/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | high | All passed | 4/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | max | Mixed | 1/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | low | Mixed | 2/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | medium | Mixed | 2/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | high | Mixed | 2/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | xhigh | Mixed | 3/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| claude-sonnet-4-6anthropic | mini-swe-agentpublished configuration | high | No passes | 0/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | low | Mixed | 3/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | medium | Mixed | 2/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | high | All passed | 4/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| gemini-3-1-pro-previewvertex_ai | mini-swe-agentpublished configuration | high | No passes | 0/4 |
| gemini-3-5-flashvertex_ai | mini-swe-agentpublished configuration | medium | Mixed | 1/4 |
| glm-5-2zai | mini-swe-agentpublished configuration | high | Mixed | 2/4 |
| glm-5-2zai | mini-swe-agentpublished configuration | max | Mixed | 2/4 |
| gpt-5-4openai | mini-swe-agentpublished configuration | xhigh | Mixed | 3/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | low | No passes | 0/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | medium | No passes | 0/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | high | Mixed | 2/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | xhigh | Mixed | 2/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | low | No passes | 0/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | medium | No passes | 0/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | high | Mixed | 1/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | xhigh | Mixed | 3/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | low | Mixed | 3/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | medium | Mixed | 2/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | high | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | low | No passes | 0/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | medium | Mixed | 1/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | high | Mixed | 1/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | xhigh | No passes | 0/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | max | Mixed | 3/4 |
| kimi-k2-7-codeopenrouter | mini-swe-agentpublished configuration | default | No passes | 0/4 |