What is respond-compromised-account?

A response workflow for a potentially compromised user account, using PICERL phases to investigate, contain, remove persistence, and restore access.

Use it to identify affected accounts and suspicious activity, assess compromise likelihood, disable accounts, reset passwords, revoke sessions, and remove unauthorized access.

It turns a suspected account takeover into a documented sequence with defined findings and response actions.

respond-compromised-account — Skill by dandye/ai-runbooks

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add dandye/ai-runbooks --skill respond-compromised-account

Clone the repo

git clone --depth 1 https://github.com/dandye/ai-runbooks

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dandye/ai-runbooks/respond-compromised-account/github.svg)](https://agentmods.dev/skills/dandye/ai-runbooks/respond-compromised-account)

Your own site

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/respond-compromised-account"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/respond-compromised-account/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/respond-compromised-account"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/respond-compromised-account.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,806 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 277
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.01806
Opus 5.5	$0.00019	$0.00722
Sonnet 5.5	$0.00009	$0.00361
Haiku 4.5	$0.00005	$0.00181

Measured 2mo ago against content hash dcef87855463, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

respond-compromised-account scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/respond-compromised-account/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compromised User Account Response Skill

Structured workflow for responding to potentially compromised user accounts using the PICERL model.

Inputs

USER_ID - Username or email of the potentially compromised user
CASE_ID - SOAR case ID for documentation
ALERT_GROUP_IDENTIFIERS - Alert group identifiers from SOAR
(Optional) INITIAL_ALERT_DETAILS - Summary of triggering alert

Required Outputs

After completing each phase, you MUST report these outputs:

Identification Phase

Output	Description
`AFFECTED_ACCOUNTS`	User accounts confirmed or suspected compromised
`SUSPICIOUS_ACTIVITY`	Summary of anomalous activity detected
`ACCESS_SCOPE`	Systems/data the account had access to
`COMPROMISE_LIKELIHOOD`	Assessment level: `Low`, `Medium`, `High`, `Confirmed`

Containment Phase

Output	Description
`DISABLED_ACCOUNTS`	Accounts that were disabled
`RESET_PASSWORDS`	Accounts with passwords reset
`REVOKED_SESSIONS`	Sessions terminated

Eradication Phase

Output	Description
`REMOVED_PERSISTENCE`	Persistence mechanisms removed (forwarding rules, OAuth apps, etc.)
`CLEANED_ENDPOINTS`	Associated endpoints verified clean

Recovery Phase

Output	Description
`RESTORED_ACCOUNTS`	Accounts re-enabled with new security controls
`USER_NOTIFICATIONS`	Users notified of incident and required actions

PICERL Phases

Phase 2: Identification

Step 2.1: Get Context

secops-soar.get_case_full_details(case_id=CASE_ID)

Use /check-duplicates.

Step 2.2: Gather Initial Context

SIEM entity lookup:

secops-mcp.lookup_entity(entity_value=USER_ID)

(If IDP tools available):

Account status
Recent logins
MFA configuration
Password last changed

Step 2.3: Analyze User Activity

Search SIEM for last 96 hours:

secops-mcp.search_security_events(
    text="All activity for USER_ID",
    hours_back=96
)

Read the full file on GitHub · 300 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 300 lines · 47 tokens per session scan A dcef87855463

Subscribe to this mod's changes

respond-compromised-account is a skill published in the GitHub repository dandye/ai-runbooks (132 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,806 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.