DD skill-security-reviewer
(no description)
As a process D 43/100 · 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.
How to improve
- Add a description to the frontmatter: without it the skill never triggers.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 12
✓ No critical or high findings
Medium and low: 12
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:851Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)- **Threat Analysis**: Attacker uses Base64 encoding to hide a curl|bash remote code execution command. After decoding, the command downloads and executes a malicious script from the attacker's server
security skill -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:560Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)| EXEC-001 | Download and execute | `curl\|bash`, `wget\|sh`, remote script execution | Critical |
tablesecurity skill -
low Risky intent
intent-offensive-securitySKILL.md:561Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| EXEC-002 | Reverse shell | `/dev/tcp`, `nc -e`, `bash -i` | Critical |
-
low Risky intent
intent-offensive-securitySKILL.md:565Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| EXEC-006 | Privilege escalation attempt | `sudo`, `su`, `doas` | Critical |
-
low Risky intent
intent-offensive-securitySKILL.md:590Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| EXFIL-007 | C2 communication | Command and control server connections | Critical |
-
low Instruction override
en-ignore-previousSKILL.md:596Instruction-override phrase ("ignore previous instructions") (documentation table row; documentation of a security skill)| INJ-001 | Instruction override | "ignore previous instructions" | Critical |
tablesecurity skill -
low Risky intent
intent-offensive-securitySKILL.md:609Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| ABUSE-002 | MCP privilege escalation | playwright/serena abuse | Critical |
A further 5 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. 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 - warning
body-longSKILL.md body ≈ 10462 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 43/100
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 40Execution cost. Instruction body is 10462 tokens: crowds the task out of the window
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 63 steps
- 100Consistency. Name and required fields are in place
- low 11 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
- +1No license
- +2Single-language instructions
- +4Structure: 36 headings
- +3Step-by-step instructions: 63 items
- +4Has examples (34 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.