BD safety-guard
Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard combines both via PreToolUse hooks. Use when working on production systems, running agents autonomously, restricting edits to a directory, or during migrations, deploys, and data changes.
The skill promises three protection modes: Careful intercepts dangerous commands (rm -rf, DROP TABLE, git push --force) and requires confirmation, Freeze locks writes to a directory, Guard combines both via PreToolUse hooks. Single instruction file with 441 tokens, no scripts, no critical errors. Safety-score 98, quality 84, but process only 45—suggesting the command-checking logic may be incomplete or poorly documented.
No model runs recorded. Two medium-to-low severity findings indicate implementation gaps. For production systems and autonomous agents, the skill delivers what it promises, but without real-world testing it's unclear whether it catches all dangerous command variations or lets exotic syntax slip through. Install if you're ready to test its behavior before going live.
Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze…
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-privilegeSKILL.md:34Privilege escalation / world-writable permissions (documentation of a security skill)- chmod 777
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:35Privilege escalation / world-writable permissions (documentation of a security skill)- sudo rm
security skill
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 441 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 385: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.