SKILLEMALL.ai
GitHub ↗ RU Sign in

CC trustmyagent

🛡️ TrustMyAgent - Security posture monitoring for AI agents. Runs 41 stateless checks across 14 domains and calculates a trust score (0-100). Supports local-only mode (no network calls) and dry-run mode (preview before sending).

ClawHub Agent Skills author: Anecdotes-Yair v1.0.0 9 files body ≈ 2 574 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureInfrastructureAI 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
C
71/100
safety, quality, tests
Safety 60%
71
Quality 40%
71
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 17

✓ No critical or high findings

Medium and low: 17
  • medium Dangerous commands cmd-persistence run.py:853
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    "crontab -e", "systemctl enable", "launchctl load",
    code literal
  • medium Dangerous commands cmd-pipe-to-shell run.py:923
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    "/etc/sudoers", "curl|bash", "curl|sh", "wget|bash",
    code literal
  • medium Dangerous commands cmd-persistence SKILL.md:106
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    (crontab -l 2>/dev/null; echo "*/15 * * * * python3 {baseDir}/run.py --quiet") | crontab -
    security skill
  • low Dangerous commands cmd-privilege checks/detection_kb.json:108
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "remediation": "Create the log directory: sudo mkdir -p /var/log && sudo chmod 755 /var/log",
    code literal
  • low Dangerous commands cmd-privilege checks/detection_kb.json:115
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "auto_remediate_command": "sudo chmod o-r /var/log/*.log 2>/dev/null"
    code literal
  • low Dangerous commands cmd-pipe-to-shell checks/detection_kb.json:155
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)
    "remediation": "1. List cron jobs: 'crontab -l'. 2. Identify suspicious entries: look for curl|bash, wget|sh, nc, ncat, reverse, rm -rf patterns. 3. Remove dangerous entries: 'crontab -e' and delete t
    detectorcode literal
  • low Dangerous commands cmd-cron-mention checks/detection_kb.json:155
    Mentions editing / listing crontab (string literal in code, not executed)
    "remediation": "1. List cron jobs: 'crontab -l'. 2. Identify suspicious entries: look for curl|bash, wget|sh, nc, ncat, reverse, rm -rf patterns. 3. Remove dangerous entries: 'crontab -e' and delete t
    code literal
  • low Dangerous commands cmd-privilege checks/detection_kb.json:240
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    "risk": "Skills with dangerous permissions (sudo, chmod 777) in their manifests can escalate privileges.",
    detectorcode literal
  • low Dangerous commands cmd-privilege checks/openclaw_checks.json:158
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    "bash_command": "FOUND=$(grep -rlE 'sudo|chmod 777|chown root|setuid|doas|pkexec|su -c|/etc/sudoers|curl.*\\|.*bash|wget.*\\|.*bash' ~/.config/openclaw/skills ~/.openclaw/skills ~/.config/claude/skill
    detectorcode literal
  • low Dangerous commands cmd-persistence checks/openclaw_checks.json:178
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    "bash_command": "if ! command -v crontab >/dev/null 2>&1; then echo '0'; elif ! crontab -l >/dev/null 2>&1; then echo '0'; else DANGEROUS=$(crontab -l 2>/dev/null | grep -v '^#' | grep -v '^$' | grep
    detectorcode literal
  • low Dangerous commands cmd-cron-mention checks/openclaw_checks.json:178
    Mentions editing / listing crontab (string literal in code, not executed)
    "bash_command": "if ! command -v crontab >/dev/null 2>&1; then echo '0'; elif ! crontab -l >/dev/null 2>&1; then echo '0'; else DANGEROUS=$(crontab -l 2>/dev/null | grep -v '^#' | grep -v '^$' | grep
    code literal
  • low Dangerous commands cmd-privilege run.py:847
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "rm -rf /", "chmod 777",
    code literal
  • low Dangerous commands cmd-cron-mention run.py:853
    Mentions editing / listing crontab (string literal in code, not executed)
    "crontab -e", "systemctl enable", "launchctl load",
    code literal
  • low Dangerous commands cmd-background-process run.py:853
    Starts a background / autostarted process (string literal in code, not executed)
    "crontab -e", "systemctl enable", "launchctl load",
    code literal
  • low Dangerous commands cmd-privilege run.py:921
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "sudo", "chmod 777", "rm -rf", "chown root", "/dev/sd",
    code literal
  • low Dangerous commands cmd-privilege run.py:922
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "setuid", "doas", "pkexec", "su -c", "su root",
    code literal
  • low Dangerous commands cmd-cron-mention SKILL.md:106
    Mentions editing / listing crontab (documentation of a security skill)
    (crontab -l 2>/dev/null; echo "*/15 * * * * python3 {baseDir}/run.py --quiet") | crontab -
    security skill

Files scanned: 9. 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")
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "repository"

Process rating: all ten parameters 54/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 6 mutating operations with no state check
  • 40Consistency. Frontmatter name (trustmyagent) differs from the folder (trust-my-agent-ai)
  • 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 70Failures and branches. 4 branches
  • 100Steps. 22 steps
  • 100Execution cost. Instruction body is 2574 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 12 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 229: enough signal without eating the budget
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 22 items
  • +4Has examples (9 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
This appears to be a real security scanner, but it needs Review because its privacy, local-only, telemetry, and social-reputation behavior are broader than users may expect.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026