{ "schema": "aiblocks-page/1", "id": "track-agent-injection-controls-and-retest-evidence", "type": "agent", "name": "Agent injection evidence review assistant", "summary": "Get safe prompt injection test cases for your AI agent, a control gap list and retest records. Tests run only with the owner's written approval.", "headline": "Agent injection evidence review assistant", "subhead": "Give it a map of your AI agent and the written scope for testing. It lists where untrusted text can reach the agent, plans safe test cases with fake data and records every result. After a fix, it tracks the retest.", "job": { "id": "secure-code", "name": "Keep your code secure" }, "level": "advanced", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-25", "inputs": [ { "type": "document", "required": true, "label": "Document", "what": "a finished document, such as a Word file, a PDF or a page of notes" }, { "type": "codebase", "required": false, "label": "Codebase", "what": "a project's code, in a folder or repo the AI can open" }, { "type": "question", "required": false, "label": "Question", "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like" } ], "outputs": [ { "type": "security_report", "required": true, "label": "Security report", "what": "the risks found in the code, ranked, each with a fix" }, { "type": "test_report", "required": true, "label": "Test report", "what": "what was tested, what passed, what failed and why" }, { "type": "plan", "required": true, "label": "Plan", "what": "a dated plan: what to do, in what order, with a decision rule for each step" }, { "type": "eval_set", "required": true, "label": "Eval set", "what": "a fixed set of test cases for an AI, each with its input and the answer that counts as a pass" } ], "you_give": [ "A map of your agent. List what it reads, each tool and its access, its memory and where its output goes (from your architecture notes).", "Written approval to test. Name the agent's owner, the exact system and accounts, the dates, the limits and a person who can stop the test.", "Safe test data, such as fake accounts, canary values that grant no access and the places test output may go", "Your current safeguards, earlier findings and a few normal tasks the agent must still do (optional)", "The agent's version or configuration ID (optional)", "Results from tests you already ran (optional)" ], "you_get": [ "A boundary map of every place untrusted text can reach the agent, what it protects and the rules that must always hold", "A control table that marks each safeguard missing, planned, implemented or verified", "A test case plan with a unique ID for each case", "A results ledger with pass, fail, blocked, error or not run for every planned case", "Findings with repeats merged, a fix for each and a retest queue", "A cleanup list of test accounts, files and canary values" ], "use_when": [ "You are about to give an AI agent tools such as email, files or a database and want to know where hostile text could steer it.", "Your agent reads outside content like web pages, support tickets or uploaded documents.", "A security reviewer asks for evidence that your injection controls work.", "You fixed a hole and need a retest that points back to the failure it came from." ], "skip_when": [ "You do not own the agent or have no written approval to test it. You get a planning checklist only, and nothing is run.", "You want to test someone else's agent, a live production system or another customer's data. It stops.", "You want a design review and fix plan with no tests. Use the Prompt injection defender.", "You already have an approved test plan and only want to run it. Use the AI agent attack tester.", "You want a general check of your code and packages. Use the Project secrets and package risk review." ], "output_sample": { "input": [ "A map of your agent, with inputs, tools, access and outputs", "Your written approval to test it", "Safe test data, such as fake accounts and canary values", "Your current safeguards and earlier findings (optional)", "Results from tests you already ran (optional)" ], "prerequisites": [ "An AI to plan and record, such as Claude, ChatGPT or Gemini", "Your own approved test setup to run the cases", "Written approval from the agent's owner" ], "output": [ { "name": "boundary-manifest.md", "contains": "Every input, tool, secret and output, which inputs outsiders can write to, the rules that must hold and each control's state." }, { "name": "case-plan.md", "contains": "Each test case with its ID, input, rule tested, fake data, expected safe result and stop condition." }, { "name": "result-ledger.md", "contains": "Pass, fail, blocked, error or not run for every planned case, with evidence and counts against the full plan." }, { "name": "findings.md", "contains": "Failures merged by cause, each with the cases, the fix and where to enforce it." }, { "name": "cleanup-status.md", "contains": "Test accounts, files and canary values to remove, each marked removed or unknown." }, { "name": "retest-queue.md", "contains": "Cases to run again after each fix, who watches for the problem and what stays open." } ] }, "output_shape": "APPROVAL | | | | | \nCONFIGURATION \n\nBOUNDARY MAP\n INPUTS | | \n TOOLS | | | \n PROTECTED | \n OUTPUTS | \n\nRULES THAT MUST HOLD\n | \n\nCONTROL TABLE\n | | | | \n\nCASE PLAN\n | | | | | | \n\nRESULTS LEDGER planned | pass | fail | blocked | error | not run\n | | |