Security & Testing Agent Skills for ChatGPT

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test…

Run Lighthouse audits and implement performance, accessibility, and SEO fixes

Use BEFORE declaring victory / shipping / committing, AND proactively for any non-trivial claim, answer, plan, or decision that would…

Report the embedded release marker when testing public Skill installation or marketplace updates.

Confine an LLM agent's actions with tool allowlists, least-privilege credentials, parameter validation, and human-in-the-loop gates.

Run multi-LLM council for adversarial debate and cross-validation.

Poison the data an LLM application trusts — its RAG knowledge base, fine-tuning corpus, or ingestion pipeline — so that later answers…

Abuse an over-privileged LLM agent — excessive tools, permissions, or autonomy — to make it perform actions beyond its intended scope…

Harden an LLM application against sensitive-data leakage by filtering and redacting model output and constraining what reaches the context.

Treat LLM output as untrusted and encode it for the specific sink that consumes it — HTML/JS context encoding, parameterized queries…

Confirm and demonstrate direct and indirect prompt injection against an LLM-backed application during an authorized assessment.

Harden an LLM application's system prompt so it carries no secrets or authorization logic and cannot be trivially extracted.

Gate every document that enters an LLM application's knowledge base or fine-tuning corpus behind source allowlisting, provenance signing…

Demonstrate unbounded resource consumption against an LLM application — token floods, unbounded output, and cost/denial-of-wallet…

Enforce tenant and user isolation in a shared vector store by filtering retrieval on an access boundary before ranking, using…

Retrieve another tenant's or another user's documents from a shared vector store by exploiting similarity search that is not bounded by an…

Performs evidence-first, read-only static analysis on authorized local executables, application binaries, and release artifacts.

Read loop-constraints.md at the start of every run and enforce every rule.

Independent verification agent for loop-produced changes.

Independent verification agent for loop-produced changes — runs tests, confirms diff scope, and issues APPROVE / REJECT / ESCALATE_HUMAN.

Use after a failure has occurred (bug shipped, test broke, deploy rolled back, data lost, security incident) — the impulse is to fix the…