SKILLEMALL.ai
GitHub ↗ RU Sign in

CC hunting-for-suspicious-scheduled-tasks

Hunts for adversary persistence and execution via Windows scheduled tasks (T1053.005) by analyzing Security Event ID 4698 task-creation events, suspicious task properties, and unusual execution patterns from schtasks.exe/at.exe. Use after detecting schtasks or at.exe in process creation logs, during incident response to enumerate persistence on compromised hosts, or when Event ID 4698 fires for an unusual task.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 8 files · 2 scripts body ≈ 1 022 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Hunts for adversary persistence and execution via Windows scheduled tasks (T1053.005) by analyzing Security Event ID 4698 task-creation events, suspicious…

As a process C 62/100 · Has gaps — weak spots: when it triggers, failures and branches, running it twice

ProcedurePeople and hiringtype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
92
Quality 40%
78
Run on models
none yet
Process rating
C
62/100
Has gaps
Failures and branches w 10
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Dangerous commands cmd-persistence SKILL.md:44
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
      - PowerShell logging for Register-ScheduledTask cmdlet usage
      security skill
    • low Risky intent intent-offensive-security SKILL.md:89
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      2. **Ransomware Staging**: Task created to run encryption payload at a future time, often during off-hours for maximum impact.
    • low Risky intent intent-offensive-security SKILL.md:92
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. **Lateral Movement via Tasks**: Remote scheduled task creation using `schtasks /create /s REMOTE_HOST` for execution on other systems.

    A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "domain"
    • note frontmatter-key unknown frontmatter key "subdomain"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    Process rating: all ten parameters 62/100

    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 22 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1022 tokens
    • 100Progress reporting. Reports progress

    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)
    • -43 reference files, but SKILL.md never points to them: the model will not open them
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 414: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 22 items
    • +3Output format is stated explicitly
    • +4Has examples (4 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.