DD outlook-entra
Microsoft Outlook via OAuth 2.0 (device code flow) et Microsoft Graph API. Lecture seule — Mail.Read, Calendars.Read, Contacts.Read.
Microsoft Outlook via OAuth 2.0 (device code flow) et Microsoft Graph API. Lecture seule — Mail.Read, Calendars.Read, Contacts.Read.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 9
-
high Dangerous commands
cmd-persistenceREADME.md:120Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v outlook_refresh; echo "55 * * * * ${SKILL_DIR}/.venv/bin/python ${SKILL_DIR}/scripts/outlook_refresh.py >> ~/.openclaw/outlook_refresh.log 2>&1" ) | crontab - -
high Dangerous commands
cmd-persistenceSKILL.md:174Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v outlook_refresh; echo "55 * * * * ${SKILL_DIR}/.venv/bin/python ${SKILL_DIR}/scripts/outlook_refresh.py >> ~/.openclaw/outlook_refresh.log 2>&1" ) | crontab -
Medium and low: 7
-
medium Exfiltration
net-redirectable-api-keyscripts/outlook_token.py:41Helper 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 Exfiltration
read-dotenvREADME.md:32Reads a .env filecp .env.example .env
-
low Dangerous commands
cmd-cron-mentionREADME.md:120Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v outlook_refresh; echo "55 * * * * ${SKILL_DIR}/.venv/bin/python ${SKILL_DIR}/scripts/outlook_refresh.py >> ~/.openclaw/outlook_refresh.log 2>&1" ) | crontab - -
low Dangerous commands
cmd-cron-mentionREADME.md:126Mentions editing / listing crontabcrontab -l | grep outlook_refresh
-
low Exfiltration
read-dotenvSKILL.md:34Reads a .env filecp .env.example .env
-
low Dangerous commands
cmd-cron-mentionSKILL.md:174Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v outlook_refresh; echo "55 * * * * ${SKILL_DIR}/.venv/bin/python ${SKILL_DIR}/scripts/outlook_refresh.py >> ~/.openclaw/outlook_refresh.log 2>&1" ) | crontab - -
low Dangerous commands
cmd-cron-mentionSKILL.md:180Mentions editing / listing crontabcrontab -l | grep outlook_refresh
Files scanned: 7. 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 46/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1718 tokens
- 100Running it twice. No mutating operations
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 132: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (8 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.