BF add-sharepoint
Use when the user wants to read or write SharePoint lists, manage documents in a SharePoint document library, or create a new SharePoint list from a Power Apps mobile app.
Use when the user wants to read or write SharePoint lists, manage documents in a SharePoint document library, or create a new SharePoint list from a Power…
As a process F 52/100 · Will not run — References files that are not bundled: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/connector-reference.md, ${PLUGIN_ROOT}/shared/connector-reference.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 4
✓ No critical or high findings
Medium and low: 4
-
medium Exfiltration
net-credential-usereferences/api-authentication-reference.md:20Credential used in a network call (verify the destination is the intended service)$token = (az account get-access-token --resource https://graph.microsoft.com --query accessToken -o tsv)
-
medium Exfiltration
net-credential-usereferences/api-authentication-reference.md:74Credential used in a network call (verify the destination is the intended service)$token = (az account get-access-token --resource https://graph.microsoft.com --query accessToken -o tsv)
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Edit Write Grep Glob Bash AskUserQuestion EnterPlanMode ExitPlanMode
-
low Secrets in code
secret-high-entropy-tokenreferences/sharepoint-reference.md:12High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `Cost ($)` | `Cost…29_` | Special chars each get `_xHHHH_` |
table
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ${PLUGIN_ROOT}/shared/shared-instructions.md - warning
missing-refreference to a missing file: ${PLUGIN_ROOT}/shared/connector-reference.md - warning
missing-refreference to a missing file: ${PLUGIN_ROOT}/shared/connector-reference.md
Process rating: all ten parameters 52/100
- 0Tools and files. 3 referenced file(s) missing: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/connector-reference.md, ${PLUGIN_ROOT}/shared/connector-reference.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 11 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Steps. 18 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1988 tokens
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 171: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.