SKILLEMALL.ai
GitHub ↗ RU Sign in

FC amber-hunter

(no description)

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: ankechenlab-node v1.2.41 MIT-0 55 files · 6 scripts body ≈ 2 524 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype 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
0/100
safety, quality, tests
Safety 60%
0
Quality 40%
0
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
When it triggers w 12
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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.

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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Add a description to the frontmatter: without it the skill never triggers.
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 · 23

  • high Dangerous commands cmd-persistence install.sh:87
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST" 2>/dev/null || true
  • high Dangerous commands cmd-persistence install.sh:99
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PROACTIVE_PLIST" 2>/dev/null || true
  • high Dangerous commands cmd-persistence install.sh:136
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    schtasks /create /tn "Amber Hunter" /tr "powershell -WindowStyle Hidden -File $SCRIPT" \
Medium and low: 20
  • medium Dangerous commands cmd-persistence CLAUDE.md:79
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl unload ~/Library/LaunchAgents/com.huper.amber-hunter.plist
    security skill
  • medium Dangerous commands cmd-persistence CLAUDE.md:80
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl load ~/Library/LaunchAgents/com.huper.amber-hunter.plist
    security skill
  • medium Exfiltration exfil-secret-in-url freeze.sh:25
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    RESULT=$(curl -s "http://loca…998/freeze?token=… -c "import urllib.parse; print(urllib.parse.quote('$TOKEN'))")" 2>/dev/null)
    quoted
  • medium Exfiltration net-credential-use freeze.sh:25
    Credential used in a network call (verify the destination is the intended service)
    RESULT=$(curl -s "http://loca…998/freeze?token=… -c "import urllib.parse; print(urllib.parse.quote('$TOKEN'))")" 2>/dev/null)
  • medium Exfiltration net-credential-use hooks/amber_precompact_hook.sh:46
    Credential used in a network call (verify the destination is the intended service)
    RESULT=$(curl -s -X POST "$AMBER_API/extract/auto?token=$TOKEN" \
  • medium Exfiltration net-credential-use hooks/amber_save_hook.sh:96
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST "$AMBER_API/extract/auto?token=$TOKEN" \
  • medium Dangerous commands cmd-persistence install.sh:82
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST="$HOME/Library/LaunchAgents/com.huper.amber-hunter.plist"
    code literal
  • medium Dangerous commands cmd-persistence install.sh:92
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PROACTIVE_PLIST="$HOME/Library/LaunchAgents/com.huper.amber-proactive.plist"
    code literal
  • medium Dangerous commands cmd-persistence README.md:234
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    ~/Library/LaunchAgents/
    security skill
  • medium Dangerous commands cmd-persistence README.md:235
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl load ~/Library/LaunchAgents/com.huper.amber-proactive.plist
    security skill
  • medium Exfiltration net-credential-use release.sh:38
    Credential used in a network call (verify the destination is the intended service)
    EXISTING=$(curl -s -H "Authorization: token $TOKEN" \
  • low Dangerous commands cmd-background-process install.sh:149
    Starts a background / autostarted process
    nohup python3 "$HUNTER_DIR/amber_hunter.py" >> "$CONFIG_DIR/amber-hunter.log" 2>&1 &

A further 8 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 46. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error name-missing SKILL.md: frontmatter has no `name`
  • error description-missing SKILL.md: no `description` — the skill can never trigger
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "protocol"
  • note frontmatter-key unknown frontmatter key "port"

Process rating: all ten parameters 55/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 1 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 20 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2524 tokens
  • 100Progress reporting. Reports progress
  • low 11 top-level sections: this looks like several domains in one skill
  • low The skill ranks results itself: that belongs to the system behind the tool, not the model

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)
  • +3Description length 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • -42 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (16 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

External checks

ClawHub: suspicious
Amber Hunter is a real local memory skill, but it has broad always-on access to conversations and files plus under-disclosed security gaps around authentication and plaintext secrets.
LLM: suspicious (high) · VirusTotal: · 29 May 2026