SKILLEMALL.ai
GitHub ↗ RU Sign in

FC truenas-skill

Manage TrueNAS SCALE via API. Check pool health, manage datasets and snapshots, monitor alerts, control services, manage apps, orchestrate Dockge container stacks, and manage bookmarks. Use when the user asks about their NAS, storage, backups, containers, bookmarks, or homelab services.

Not recommendedlow grade F
ClawHub Agent Skills author: anotb v1.2.0 14 files body ≈ 2 581 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice

IntegrationInfrastructureData 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
F
36/100
safety, quality, tests
Safety 60%
0
Quality 40%
91
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 28

    ✓ No critical or high findings

    Medium and low: 28
    • medium Exfiltration net-credential-use references/books-and-media.md:26
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$AUDIOBOOKSHELF_URL/api/libraries" -H "Authorization: Bearer $AUDIOBOOKSHELF_API_KEY"
    • medium Exfiltration net-credential-use references/books-and-media.md:45
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$LAZYLIBRARIAN_URL/api?cmd=getVersion&apikey=$LAZYLIBRARIAN_API_KEY"
    • medium Exfiltration net-credential-use references/books-and-media.md:48
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$LAZYLIBRARIAN_URL/api?cmd=searchBook&name=QUERY&apikey=$LAZYLIBRARIAN_API_KEY"
    • medium Exfiltration net-credential-use references/books-and-media.md:51
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$LAZYLIBRARIAN_URL/api?cmd=findAuthor&name=AUTHOR&apikey=$LAZYLIBRARIAN_API_KEY"
    • medium Exfiltration net-credential-use references/books-and-media.md:54
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$LAZYLIBRARIAN_URL/api?cmd=getWanted&apikey=$LAZYLIBRARIAN_API_KEY"
    • medium Exfiltration net-credential-use references/downloads.md:37
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SABNZBD_URL/api?mode=queue&output=json&apikey=$SABNZBD_API_KEY"
    • medium Exfiltration net-credential-use references/downloads.md:40
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SABNZBD_URL/api?mode=history&output=json&apikey=$SABNZBD_API_KEY"
    • medium Exfiltration net-credential-use references/downloads.md:43
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SABNZBD_URL/api?mode=pause&apikey=$SABNZBD_API_KEY"
    • medium Exfiltration net-credential-use references/downloads.md:46
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SABNZBD_URL/api?mode=resume&apikey=$SABNZBD_API_KEY"
    • medium Exfiltration net-credential-use references/downloads.md:72
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SABNZBD_URL/api?mode=queue&output=json&apikey=$SABNZBD_API_KEY" \
    • medium Exfiltration net-credential-use references/homelab-services.md:36
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SYNCTHING_URL/rest/system/status" -H "X-API-Key: $SYNCTHING_API_KEY"
    • medium Exfiltration net-credential-use references/homelab-services.md:39
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SYNCTHING_URL/rest/system/connections" -H "X-API-Key: $SYNCTHING_API_KEY"
    • medium Exfiltration net-credential-use references/homelab-services.md:42
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$SYNCTHING_URL/rest/db/status?folder=FOLDER_ID" -H "X-API-Key: $SYNCTHING_API_KEY"
    • medium Exfiltration net-credential-use references/homelab-services.md:62
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$NOCODB_URL/api/v2/meta/bases" -H "xc-token: $NOCODB_API_KEY"
    • medium Exfiltration net-credential-use references/homelab-services.md:65
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$NOCODB_URL/api/v2/meta/bases/BASE_ID/tables" -H "xc-token: $NOCODB_API_KEY"
    • medium Exfiltration net-credential-use references/media-management.md:24
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$OVERSEERR_URL/api/v1/search?query=QUERY" -H "X-Api-Key: $OVERSEERR_API_KEY"
    • medium Exfiltration net-credential-use references/media-management.md:31
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$OVERSEERR_URL/api/v1/movie/TMDB_ID" -H "X-Api-Key: $OVERSEERR_API_KEY"
    • medium Exfiltration net-credential-use references/media-management.md:34
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$OVERSEERR_URL/api/v1/tv/TMDB_ID" -H "X-Api-Key: $OVERSEERR_API_KEY"
    • medium Exfiltration net-credential-use references/media-management.md:40
      Credential used in a network call (verify the destination is the intended service)
      curl -X POST "$OVERSEERR_URL/api/v1/request" -H "X-Api-Key: $OVERSEERR_API_KEY" \
    • medium Exfiltration net-credential-use references/media-management.md:86
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$OVERSEERR_URL/api/v1/request?take=20&filter=pending" -H "X-Api-Key: $OVERSEERR_API_KEY"
    • medium Exfiltration net-credential-use SKILL.md:117
      Credential used in a network call (verify the destination is the intended service)
      curl -sk "$TRUENAS_URL/api/v2.0/system/info" -H "Authorization: Bearer $TRUENAS_API_KEY"
    • medium Exfiltration net-credential-use SKILL.md:124
      Credential used in a network call (verify the destination is the intended service)
      curl -sk "$TRUENAS_URL/api/v2.0/pool" -H "Authorization: Bearer $TRUENAS_API_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:136
      Credential used in a network call (verify the destination is the intended service)
      curl -sk "$TRUENAS_URL/api/v2.0/alert/list" -H "Authorization: Bearer $TRUENAS_API_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:143
      Credential used in a network call (verify the destination is the intended service)
      curl -sk "$TRUENAS_URL/api/v2.0/service" -H "Authorization: Bearer $TRUENAS_API_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:152
      Credential used in a network call (verify the destination is the intended service)
      curl -sk "$TRUENAS_URL/api/v2.0/pool/dataset" -H "Authorization: Bearer $TRUENAS_API_KEY" \
    • low Secrets in code secret-high-entropy-token package-lock.json:24
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…GLw+xYSd…cqA==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:54
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…CzX+oOPq…N14+GARU…vzg==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:90
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…X9X+a368j/Ft0w…TWZ/g==",
      detector

    Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 57/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 5 mutating operations with no state check
    • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2581 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 11 top-level sections: this looks like several domains in one skill

    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
    • +2Single-language instructions
    • +3Description length 287: enough signal without eating the budget
    • +4Structure: 43 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (26 code blocks)
    • +4Reference files are cited in the instructions (6 of 6)
    • +3All 3 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    This skill appears purpose-built for homelab administration, but it gives an agent broad, high-impact control with unsafe credential-transport defaults and weak confirmation boundaries.
    LLM: suspicious (high) · VirusTotal: suspicious · 10 Sept 2026