BB dep-audit
Audit project dependencies for known vulnerabilities (CVEs). Supports npm, pip, Cargo, and Go. Zero API keys required. Safe-by-default: report-only mode, fix commands require confirmation.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/detect.sh:87Pipe-to-shell installer from a well-known host (still executes remote code) (detector / deny-list definition; string literal in code, not executed)syft_info=$(tool_info "syft" "version" "curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh")
detectorcode literal -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/sbom.sh:43Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)emit_error "syft not found. Install with: curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b /usr/local/bin" "$DIR"
code literal
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (git, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 35 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1565 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 188: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (6 code blocks)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.