BD add-managed-cli
Add or upgrade a curated, immutable managed CLI for Sim Function sandboxes, including client-safe catalog metadata, a pinned server-only installation recipe, checksum and executable verification, provider compatibility, PATH propagation, content-addressed image identity, and tests. Use when adding a CLI to the Sandbox managed-CLI selector or changing an existing managed CLI version or recipe.
Add or upgrade a curated, immutable managed CLI for Sim Function sandboxes, including client-safe catalog metadata, a pinned server-only installation recipe…
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Concealment
en-hide-from-userSKILL.md:48Instruction to hide actions from the user (documentation of a security skill)Before shipping the first upgrade for a tool family, verify that editing a sandbox cannot leave both the retired and replacement IDs selected. If the generic selector and API validation do not already
security skill
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 91): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 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
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2318 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 395: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.