SKILLEMALL.ai
GitHub ↗ RU Sign in

CB collecting-indicators-of-compromise

Systematically collects, categorizes, and distributes indicators of compromise (IOCs) during and after security incidents to enable detection, blocking, and threat intelligence sharing. Covers network, host, email, and behavioral indicators using STIX/TAXII formats and threat intelligence platforms. Activates for requests involving IOC collection, indicator extraction, threat indicator sharing, compromise indicators, STIX export, or IOC enrichment.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 2 460 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Systematically collects, categorizes, and distributes indicators of compromise (IOCs) during and after security incidents to enable detection, blocking, and…

As a process B 70/100 · Nearly there — weak spots: 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
B
70/100
Nearly there
Failures and branches w 10
0
Running it twice w 4
30
When it triggers w 12
50
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:117
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
      - Registry modified:  HKCU\Software\Microsoft\Windows\CurrentVersion\Run\svcupdate
      security skill
    • low Risky intent intent-offensive-security SKILL.md:111
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **From Malware Analysis:**
    • low Risky intent intent-offensive-security SKILL.md:182
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      "name": "Qakbot C2 Server IP",
      quoted
    • low Risky intent intent-offensive-security SKILL.md:248
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      IPv4     | 185.220.101[.]42         | 95         | Qakbot C2 server

    Files scanned: 4. 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 "mitre_attack"
    • note frontmatter-key unknown frontmatter key "nist_csf"

    Process rating: all ten parameters 70/100

    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 7 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 48 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2460 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
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • -31 of 1 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 452: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 48 items
    • +3Output format is stated explicitly
    • +4Has examples (6 code blocks)
    • +1License stated

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