SKILLEMALL.ai
GitHub ↗ RU Sign in

FF proactive-amcp

Proactive immortal — behavior ontology (learn remember stuck) hooks kick in · IPFS soul · Solvr · self-heals on boot · disk check · watchdog 🏴‍☠️

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 58 files · 44 scripts body ≈ 4 372 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Proactive immortal — behavior ontology (learn remember stuck) hooks kick in · IPFS soul · Solvr · self-heals on boot · disk check · watchdog 🏴‍☠️

As a process F 41/100 · Will not run — References files that are not bundled: docs/WATCHDOG-RECOVERY.md

ProcedureAI and agentstype 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
24/100
safety, quality, tests
Safety 60%
0
Quality 40%
61
Run on models
none yet
Process rating
F
41/100
Will not run
References files that are not bundled: docs/WATCHDOG-RECOVERY.md
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

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. 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 · 26

  • high Dangerous commands cmd-persistence scripts/init-services.sh:93
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    { crontab -l 2>/dev/null || true; echo "$cron_line"; } | crontab -
  • high Dangerous commands cmd-persistence scripts/init-services.sh:208
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    { crontab -l 2>/dev/null || true; echo "$cron_line"; } | crontab -
  • high Dangerous commands cmd-persistence scripts/install.sh:309
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    { crontab -l 2>/dev/null || true; echo "$cron_line"; } | crontab -
  • high Dangerous commands cmd-persistence scripts/install.sh:391
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    { crontab -l 2>/dev/null || true; echo "$cron_line"; } | crontab -
Medium and low: 22
  • medium Exfiltration net-redirectable-api-key scripts/generate-problem-summary.py:95
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Dangerous commands cmd-persistence scripts/init-services.sh:90
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v "# amcp-watchdog" | { cat; echo "$cron_line"; } | crontab -
    detector
  • medium Dangerous commands cmd-persistence scripts/init-services.sh:206
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v "# amcp-checkpoint" | { cat; echo "$cron_line"; } | crontab -
    detector
  • medium Dangerous commands cmd-persistence scripts/install.sh:307
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v "# amcp-watchdog" | { cat; echo "$cron_line"; } | crontab -
    detector
  • medium Dangerous commands cmd-persistence scripts/install.sh:389
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v "# amcp-checkpoint" | { cat; echo "$cron_line"; } | crontab -
    detector
  • medium Dangerous commands cmd-pipe-to-shell scripts/install.sh:443
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    if curl -sL --connect-timeout 10 --max-time 30 "https://solvr.dev/install.sh" | bash 2>/dev/null; then
    vendor-host
  • medium Dangerous commands cmd-pipe-to-shell scripts/install.sh:472
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    if curl -sL --connect-timeout 10 --max-time 60 "https://solvr.dev/install.sh" | bash 2>/dev/null; then
    vendor-host
  • low Dangerous commands cmd-background-process scripts/_config-fix.sh:101
    Starts a background / autostarted process
    nohup openclaw gateway start > /tmp/openclaw-gateway.log 2>&1 &
  • low Secrets in code secret-anthropic-key scripts/_diagnose-claude.sh:134
    Anthropic API key (placeholder value)
    log_error "  proactive-amcp config set anthropic.apiKey sk-a…KEY"
    placeholder
  • low Dangerous commands cmd-cron-mention scripts/init-services.sh:87
    Mentions editing / listing crontab
    if crontab -l 2>/dev/null | grep -q "# amcp-watchdog"; then
  • low Dangerous commands cmd-cron-mention scripts/init-services.sh:90
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v "# amcp-watchdog" | { cat; echo "$cron_line"; } | crontab -
  • low Dangerous commands cmd-cron-mention scripts/init-services.sh:93
    Mentions editing / listing crontab
    { crontab -l 2>/dev/null || true; echo "$cron_line"; } | crontab -
  • low Dangerous commands cmd-cron-mention scripts/init-services.sh:97
    Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)
    info "View: crontab -l | grep amcp"
    detectorcode literal
  • low Dangerous commands cmd-cron-mention scripts/init-services.sh:204
    Mentions editing / listing crontab
    if crontab -l 2>/dev/null | grep -q "# amcp-checkpoint"; then
  • low Dangerous commands cmd-cron-mention scripts/install.sh:306
    Mentions editing / listing crontab
    if crontab -l 2>/dev/null | grep -q "# amcp-watchdog"; then
  • low Dangerous commands cmd-cron-mention scripts/install.sh:307
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v "# amcp-watchdog" | { cat; echo "$cron_line"; } | crontab -
  • low Dangerous commands cmd-cron-mention scripts/install.sh:309
    Mentions editing / listing crontab
    { crontab -l 2>/dev/null || true; echo "$cron_line"; } | crontab -
  • low Dangerous commands cmd-cron-mention scripts/install.sh:388
    Mentions editing / listing crontab
    if crontab -l 2>/dev/null | grep -q "# amcp-checkpoint"; then
  • low Dangerous commands cmd-cron-mention scripts/install.sh:389
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v "# amcp-checkpoint" | { cat; echo "$cron_line"; } | crontab -
  • low Dangerous commands cmd-background-process scripts/restore-agent.sh:394
    Starts a background / autostarted process
    nohup openclaw gateway start > /tmp/openclaw-gateway.log 2>&1 &
  • low Dangerous commands cmd-cron-mention SECURITY.md:184
    Mentions editing / listing crontab (documentation of a security skill)
    crontab -l | grep -v 'amcp\|checkpoint\|watchdog' | crontab -
    security skill

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

Files scanned: 58. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: docs/WATCHDOG-RECOVERY.md
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "triggers"

Process rating: all ten parameters 41/100

Will not run. References files that are not bundled: docs/WATCHDOG-RECOVERY.md
  • 0Tools and files. 1 referenced file(s) missing: docs/WATCHDOG-RECOVERY.md
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 10 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 4372 tokens
  • 85Steps. 30 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • low 18 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 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
  • -351 of 55 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 146: enough signal without eating the budget
  • +4Structure: 49 headings
  • +3Step-by-step instructions: 30 items
  • +4Has examples (29 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.