SKILLEMALL.ai
GitHub ↗ RU Sign in

DF epo-patent-intelligence

(no description)

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: quratus v1.0.0 MIT-0 73 files · 15 scripts body ≈ 2 806 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 37/100 · Will not run — References files that are not bundled: scripts/weekly_report.sh, references/REPORT_TEMPLATES.md, references/COMPETITOR_SETUP.md

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
D
52/100
safety, quality, tests
Safety 60%
46
Quality 40%
60
Run on models
none yet
Process rating
F
37/100
Will not run
References files that are not bundled: scripts/weekly_report.sh, references/REPORT_TEMPLATES.md, references/COMPETITOR_SETUP.md
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
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.

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. 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 · 33

  • high Dangerous commands cmd-persistence scripts/setup_cron.sh:38
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null; echo "$CRON_ENTRY") | crontab -
Medium and low: 32
  • medium Dangerous commands cmd-persistence scripts/setup_cron.sh:34
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v "weekly_automation_enhanced.sh" | crontab -
    detector
  • low Obfuscation obf-base64-blob docs/DASHBOARD_RECOVERY_PROCEDURES.md:102
    Long base64-looking blob (quoted — discussed, not commanded)
    export TUNNEL_TOKEN="eyJh…WW1
    quoted
  • low Exfiltration net-credential-use docs/DASHBOARD_RECOVERY_PROCEDURES.md:103
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    cloudflared tunnel --no-autoupdate run --token "$TUNNEL_TOKEN" --url http://loca…080 2>&1 &
    quoted
  • low Dangerous commands cmd-cron-mention docs/MAINTENANCE_PROCEDURES.md:211
    Mentions editing / listing crontab
    crontab -l | grep "weekly_automation"
  • low Dangerous commands cmd-cron-mention scripts/health_monitor.sh:163
    Mentions editing / listing crontab
    if crontab -l 2>/dev/null | grep -q "weekly_automation_enhanced.sh"; then
  • low Dangerous commands cmd-background-process scripts/restart_tunnel_kw16.sh:10
    Starts a background / autostarted process
    nohup python3 -m http.server 8080 > /tmp/http…log 2>&1 &
  • low Obfuscation obf-base64-blob scripts/restart_tunnel_kw16.sh:13
    Long base64-looking blob (quoted — discussed, not commanded)
    export TUNNEL_TOKEN="eyJh…WW1
    quoted
  • low Exfiltration net-credential-use scripts/restart_tunnel_kw16.sh:14
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    nohup cloudflared tunnel --no-autoupdate run --token "$TUNNEL_TOKEN" --url http://loca…080 > /tmp/tunn…log 2>&1 &
    quoted
  • low Dangerous commands cmd-background-process scripts/restart_tunnel_kw17.sh:10
    Starts a background / autostarted process
    nohup python3 -m http.server 8080 > /tmp/http…log 2>&1 &
  • low Obfuscation obf-base64-blob scripts/restart_tunnel_kw17.sh:13
    Long base64-looking blob (quoted — discussed, not commanded)
    export TUNNEL_TOKEN="eyJh…WW1
    quoted
  • low Exfiltration net-credential-use scripts/restart_tunnel_kw17.sh:14
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    nohup cloudflared tunnel --no-autoupdate run --token "$TUNNEL_TOKEN" --url http://loca…080 > /tmp/tunn…log 2>&1 &
    quoted
  • low Dangerous commands cmd-background-process scripts/restart_tunnel.sh:9
    Starts a background / autostarted process
    nohup python3 -m http.server 8080 > /tmp/http_server_fresh.log 2>&1 &
  • low Obfuscation obf-base64-blob scripts/restart_tunnel.sh:12
    Long base64-looking blob (quoted — discussed, not commanded)
    export TUNNEL_TOKEN="eyJh…WW1
    quoted
  • low Exfiltration net-credential-use scripts/restart_tunnel.sh:13
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    nohup cloudflared tunnel --no-autoupdate run --token "$TUNNEL_TOKEN" --url http://loca…080 > /tmp/tunnel.log 2>&1 &
    quoted
  • low Dangerous commands cmd-background-process scripts/rotate_weekly.sh:60
    Starts a background / autostarted process
    nohup python3 -m http.server 8080 > /tmp/http_server_kw$WEEK.log 2>&1 &
  • low Obfuscation obf-base64-blob scripts/rotate_weekly.sh:63
    Long base64-looking blob (quoted — discussed, not commanded)
    export TUNNEL_TOKEN="eyJh…WW1
    quoted
  • low Exfiltration net-credential-use scripts/rotate_weekly.sh:64
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    nohup cloudflared tunnel --no-autoupdate run --token "\$TUNNEL_TOKEN" --url http://loca…080 > /tmp/tunnel_kw$WEEK.log 2>&1 &
    quoted
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:31
    Mentions editing / listing crontab
    if crontab -l 2>/dev/null | grep -q "weekly_automation_enhanced.sh"; then
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:34
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v "weekly_automation_enhanced.sh" | crontab -
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:38
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null; echo "$CRON_ENTRY") | crontab -
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:58
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -A2 -B2 "weekly_automation"
  • low Obfuscation obf-base64-blob scripts/start_cloudflare_tunnel.sh:28
    Long base64-looking blob (quoted — discussed, not commanded)
    export TUNNEL_TOKEN="eyJh…WW1
    quoted
  • low Exfiltration net-credential-use scripts/start_cloudflare_tunnel.sh:31
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    cloudflared tunnel --no-autoupdate run --token "$TUNNEL_TOKEN" --url http://loca…080 2>&1 &
    quoted
  • low Obfuscation obf-base64-blob scripts/start_tunnel.sh:26
    Long base64-looking blob (quoted — discussed, not commanded)
    export TUNNEL_TOKEN="eyJh…WW1
    quoted
  • low Exfiltration net-credential-use scripts/start_tunnel.sh:27
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    cloudflared tunnel --no-autoupdate run --token "$TUNNEL_TOKEN" --url http://loca…080 &
    quoted
  • low Exfiltration read-dotenv SKILL.md:27
    Reads a .env file
    source .env
  • low Exfiltration read-dotenv SKILL.md:58
    Reads a .env file
    cat .env
  • low Exfiltration read-dotenv SKILL.md:65
    Reads a .env file
    source .env
  • low Exfiltration read-dotenv SKILL.md:178
    Reads a .env file
    1. Source .env credentials
  • low Dangerous commands cmd-cron-mention SKILL.md:190
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention SKILL.md:325
    Mentions editing / listing crontab
    crontab -e
  • low Exfiltration read-dotenv SKILL.md:334
    Reads a .env file (detector / deny-list definition)
    - Script loads via `source .env` before execution
    detector

Files scanned: 73. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: European Patent Office (EPO) patent intelligence and competitive a… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning missing-ref reference to a missing file: scripts/weekly_report.sh
  • warning missing-ref reference to a missing file: references/REPORT_TEMPLATES.md
  • warning missing-ref reference to a missing file: references/COMPETITOR_SETUP.md

Process rating: all ten parameters 37/100

Will not run. References files that are not bundled: scripts/weekly_report.sh, references/REPORT_TEMPLATES.md, references/COMPETITOR_SETUP.md
  • 0Tools and files. 3 referenced file(s) missing: scripts/weekly_report.sh, references/REPORT_TEMPLATES.md, references/COMPETITOR_SETUP.md
  • 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. 6 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 115 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2806 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 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)
  • +3Description length 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -320 of 22 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 115 items
  • +4Has examples (11 code blocks)
  • +4Reference files are cited in the instructions (2 of 14)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: suspicious
This skill is a plausible patent-reporting tool, but it includes hard-coded tunnel credentials and scripts that can publish local reports to an external Cloudflare domain with more authority and less disclosure than users should accept unchecked.
LLM: suspicious (high) · VirusTotal: malicious · 27 May 2026