BC outlook
Read, search, and manage Outlook emails and calendar via Microsoft Graph API. Use when the user asks about emails, inbox, Outlook, Microsoft mail, calendar events, or scheduling.
Read, search, and manage Outlook emails and calendar via Microsoft Graph API.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Exfiltration
net-credential-usescripts/outlook-mail.sh:284Credential used in a network call (verify the destination is the intended service)curl -s "$API/mailFolders" -H "Authorization: Bearer $ACCESS_TOKEN" | jq -r '.value[].displayName'
-
medium Exfiltration
net-credential-usescripts/outlook-mail.sh:409Credential used in a network call (verify the destination is the intended service)curl -s "$API/messages/$FULL_ID/attachments" -H "Authorization: Bearer $ACCESS_TOKEN" | jq -r '.value[].name'
-
medium Exfiltration
net-credential-usescripts/outlook-mail.sh:649Credential used in a network call (verify the destination is the intended service)curl -s "$API/messages?\$search=\"$KEYWORD\"&\$top=20&\$select=id,subject,from,receivedDateTime" \
-
medium Dangerous commands
cmd-pipe-to-shellscripts/outlook-setup.sh:29Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)echo "Install with: curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash"
code literal -
low Exfiltration
net-credential-usereferences/setup.md:91Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)-d "client_id=$CLIENT_ID&client_secret=$CLIENT_SECRET&code=$AUTH_CODE&redirect_uri=http://localhost&grant_type=…&scope=… https://graph.microso
vendor-hostquoted -
low Dangerous commands
cmd-privilegescripts/outlook-setup.sh:29Privilege escalation / world-writable permissions (string literal in code, not executed)echo "Install with: curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash"
code literal -
low Exfiltration
net-credential-usescripts/outlook-token.sh:27Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)-d "client_id=$CLIENT_ID&client_secret=$CLIENT_SECRET&refresh_token=$REFRESH_TOKEN&grant_type=refresh_token&scope=https://graph.microsoft.com/Mail.ReadWrite https://graph.microsoft.com/Mail.Send https
vendor-hostquoted
Files scanned: 6. 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 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 42 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1730 tokens
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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 178: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.