SKILLEMALL.ai
GitHub ↗ RU Sign in

BF alibabacloud-ak-leak-incident-response

Investigate an Alibaba Cloud AccessKey (AK) leakage incident and produce a read-only investigation report. Use when the user reports a leaked / exposed / stolen / compromised Alibaba Cloud AccessKey (AK / AK-SK / access key / secret key / RAM credential); receives an AK-leak alert, risk notification, SMS, or email; finds an AK/secret exposed on GitHub, Gitee, a public repo, logs, or config files; needs AK-leak incident response, post-theft investigation, or risk assessment; or wants to trace a leaked AK's malicious operations, attack chain, created sub-users (RAM users), or new AccessKeys.

ClawHub Agent Skills author: alibabacloud-skills-team v0.0.1 MIT-0 18 files body ≈ 2 664 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Investigate an Alibaba Cloud AccessKey (AK) leakage incident and produce a read-only investigation report.

As a process F 56/100 · Will not run — References files that are not bundled: scripts/query_*.py

GeneratorGitHubInfrastructureData and analyticstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
95
Quality 40%
79
Run on models
none yet
Process rating
F
56/100
Will not run
References files that are not bundled: scripts/query_*.py
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 5

✓ No critical or high findings

Medium and low: 5
  • low Risky intent intent-offensive-security references/module3_actiontrail_audit.md:164
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | `Ram` | Sub-account creation, privilege escalation | ALL/AK/IP/Service |
  • low Risky intent intent-offensive-security references/module3_actiontrail_audit.md:183
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    | **HIGH** | `CreateUser`, `CreateAccessKey`, `AttachPolicyToUser`, `RunInstances`, `CreateInstance`, `SendSms`, `AddDomainRecord` | Account creation, privilege escalation, resource provisioning |
    detector
  • low Risky intent intent-offensive-security references/module4_timeline_report.md:124
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Privilege escalation | HIGH | Admin policies attached to rogue sub-accounts |
  • low Risky intent intent-offensive-security references/module5_remediation_best_practices.md:43
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Why**: Attacker-created ECS instances may be used for cryptocurrency mining, C2 relay, DDoS, or lateral movement. Each minute of operation incurs billing and increases liability.
  • low Risky intent intent-offensive-security references/module5_remediation_best_practices.md:188
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Sub-user creation + privilege escalation | Delete sub-users + their AKs + policies | Rotate all account AKs | Enable MFA, audit all RAM policies |

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/query_*.py

Process rating: all ten parameters 56/100

Will not run. References files that are not bundled: scripts/query_*.py
  • 0Tools and files. 1 referenced file(s) missing: scripts/query_*.py
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 11 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 10 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2664 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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
  • -33 of 6 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 596: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 10 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (7 of 9)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: suspicious
This is mostly a read-only Alibaba Cloud leak investigation skill, but it reaches broader account audit and identity data than the narrow leaked-key framing implies and can optionally install a dependency at runtime.
LLM: suspicious (high) · VirusTotal: · 24 Aug 2026