CC continuous-llm-red-teaming-with-promptfoo
Wires Promptfoo and DeepTeam into CI/CD for automated, repeatable red-teaming of LLM apps against OWASP LLM Top 10, OWASP Agentic, and MITRE ATLAS presets, failing the build when jailbreak or injection vulnerabilities regress. Use for continuous adversarial testing in CI/CD, a merge-blocking security gate, or comparing model/prompt versions for compliance reporting.
Wires Promptfoo and DeepTeam into CI/CD for automated, repeatable red-teaming of LLM apps against OWASP LLM Top 10, OWASP Agentic, and MITRE ATLAS presets…
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 6
✓ No critical or high findings
Medium and low: 6
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:48Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `deepteam run config.yaml` | Run red teaming from a YAML config |
-
low Risky intent
intent-offensive-securityreferences/standards.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Standards and References — Continuous LLM Red Teaming with Promptfoo
-
low Risky intent
intent-offensive-securitySKILL.md:23Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Continuous LLM Red Teaming with Promptfoo
-
low Risky intent
intent-offensive-securitySKILL.md:69Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| AML.T0054 | LLM Jailbreak | Privilege Escalation / Defense Evasion (LLM) |
-
low Risky intent
intent-offensive-securitySKILL.md:147Offensive-security / dual-use content (legitimate for authorised testing; review intended use)name: LLM Red Team
-
low Risky intent
intent-offensive-securitySKILL.md:157Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- name: Run red team (fails build on new vulns)
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "nist_ai_rmf" - note
frontmatter-keyunknown frontmatter key "atlas_techniques"
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2278 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 368: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.