DD clawsec-monitor
(no description)
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
How to improve
- Add a description to the frontmatter: without it the skill never triggers.
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Dangerous commands
cmd-encoded-execREADME.md:35Executes a base64/encoded payload (detector / deny-list definition; documentation table row)| **Command injection** | `curl … \| bash`, `wget … \| sh`, `eval`, `base64 -d \| sh` |
detectortable -
medium Secrets in code
secret-private-keyrun_tests.py:126Private key material (key header without key body; test fixture / example file; quoted — discussed, not commanded)b"X-Data: -----BEGIN PRIVATE KEY----- …
header onlyfixturequoted -
medium Dangerous commands
cmd-privilegeskill.md:102Privilege escalation / world-writable permissionssudo cp /tmp/clawsec/ca.crt /usr/local/share/ca-certificates/clawsec.crt
-
medium Dangerous commands
cmd-pipe-to-shellskill.md:139Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| `pipe_to_shell` | `curl <url> \| bash`, `wget <url> \| sh` |
table -
low Dangerous commands
cmd-privilegeclawsec-monitor.py:24Privilege escalation / world-writable permissions (string literal in code, not executed)sudo cp /tmp/clawsec/ca.crt /usr/local/share/ca-certificates/clawsec.crt && sudo update-ca-certificates
code literal -
low Dangerous commands
cmd-pipe-to-shellREADME.md:35Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; documentation table row)| **Command injection** | `curl … \| bash`, `wget … \| sh`, `eval`, `base64 -d \| sh` |
detectortable -
low Risky intent
intent-offensive-securityREADME.md:37Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **SSH lateral movement** | New outbound SSH connections to unknown hosts |
-
low Dangerous commands
cmd-privilegeREADME.md:75Privilege escalation / world-writable permissions (documentation table row)| Ubuntu/Debian | `sudo cp /tmp/clawsec/ca.crt /usr/local/share/ca-certificates/clawsec.crt && sudo update-ca-certificates` |
table -
low Secrets in code
secret-high-entropy-tokenrun_tests.py:112High-entropy token-like string (may be an id, hash or a credential) (placeholder value)pubkey = "ssh-rsa AAAA…key+fakekey+fakekey+fakekey+fakekey=="
placeholder -
low Secrets in code
secret-anthropic-keyrun_tests.py:275Anthropic API key (placeholder value)payload = b"GET http://x.com/?t=… HTTP/1.0\r\nHost: x.com\r\n\r\n"
placeholder
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 49/100
- 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. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1723 tokens
- 100Progress reporting. Reports progress
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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)
- +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
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.