Results for “failure-injection”

`analysis-agent`/`task-agent`/`review-agent`: use when symptoms, logs, metrics, regressions, or incidents need cause analysis; skip when no diagnosis decision exists.

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

`analysis-agent`/`task-agent`/`review-agent`: use when repeated failure needs a new hypothesis or proof path; skip an initial failure with verified cause and a different action.

Reproduce a bug as a failing regression test, fix until green, review, and commit via a delegated pipeline.

Find the earliest decisive failure in an agent run trace and propose an evidence-backed targeted repair. Load when a run failed, results are wrong, or the user asks what went wrong in an agent session. Also triggers on "localize the fault", "first incorrect step", "debug this run", "trace attribution", "why did the agent fail", or after run-trace captures errors. Pairs with debug-and-fix for code defects and dynamic-routing for plan faults.

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for

`analysis-agent`/`task-agent`/`review-agent`: use when retryable, terminal, timeout, partial-failure, or fallback semantics change across boundaries; skip unchanged failures.

Review docs, tool output, skills, and memory candidates for prompt-injection risk.