BF skill-hr
Use when the user starts a new multi-step task, asks to pick/install/manage skills, tune skill performance, or fire/remove a skill after failure. Acts as HR for the Skill ecosystem: JD intake, internal bench matching, vetted market recruitment, delegation handoffs, and HRIS-style performance logging with probation/termination. Does not replace domain skills' internal workflows.
As a process F 39/100 · Will not run — References files that are not bundled: references/prompts/P01
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Exfiltration
net-redirectable-api-keyscripts/generate_cases.py:320Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/run_matching_benchmark_llm.py:184Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Dangerous commands
cmd-pipe-to-shellreferences/01-competency-model.md:29Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)| **Blind pipe** | `curl \| sh` / remote code without readable source and license |
tablesecurity skill -
low Dangerous commands
cmd-pipe-to-shellreferences/08-framework-evaluation.md:89Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)- No silent physical uninstall / no `curl | sh` encouragement
negated
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/prompts/P01
Process rating: all ten parameters 39/100
- 0Tools and files. 1 referenced file(s) missing: references/prompts/P01
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1320 tokens
- 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
- +4No input/output examples
- -31 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 380: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 12 items
- +4Reference files are cited in the instructions (10 of 10)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.