SKILLEMALL.ai

CC onedrive

Read, manage, share, upload, and download OneDrive files via Microsoft Graph API. Use when the user asks about OneDrive, OneDrive for Business, SharePoint document libraries, file sharing, or cloud storage on Microsoft.

ClawHub Agent Skills author: trendex v1.0.0 MIT-0 11 files · 5 scripts body ≈ 2 571 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
C
65/100
safety, quality, tests
Safety 60%
47
Quality 40%
91
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

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.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

    For the model run — optional
    • 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 · 13

    ✓ No critical or high findings

    Medium and low: 13
    • medium Dangerous commands cmd-shell-rc scripts/onedrive-bootstrap.sh:165
      Writes to a shell startup file
      echo "[onedrive/setup] updating ~/.bashrc env exports..."
    • medium Dangerous commands cmd-shell-rc scripts/onedrive-bootstrap.sh:166
      Writes to a shell startup file
      sed -i '/ONEDRIVE_MCP/d' ~/.bashrc 2>/dev/null || true
    • medium Dangerous commands cmd-shell-rc scripts/onedrive-bootstrap.sh:167
      Writes to a shell startup file
      cat <<'EOF' >> ~/.bashrc
    • medium Exfiltration net-credential-use scripts/onedrive-files.sh:60
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -H "Authorization: Bearer $token" "$url?\$select=id" | jq -r '.id'
    • medium Exfiltration net-credential-use scripts/onedrive-files.sh:66
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS "$GRAPH$path" -H "Authorization: Bearer $token"
    • medium Exfiltration net-credential-use scripts/onedrive-files.sh:82
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS "$url" -H "Authorization: Bearer $token" \
    • medium Exfiltration net-credential-use scripts/onedrive-files.sh:130
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS "$url" -H "Authorization: Bearer $token" | jq
    • medium Exfiltration net-credential-use scripts/onedrive-files.sh:148
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS "$url" -H "Authorization: Bearer $token" \
    • medium Dangerous commands cmd-pipe-to-shell scripts/onedrive-setup.sh:28
      Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
      echo "  - Azure CLI: curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash"
      code literal
    • medium Exfiltration net-credential-use scripts/onedrive-share.sh:111
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS "$url" -H "Authorization: Bearer $token" \
    • low Exfiltration net-credential-use scripts/onedrive-bootstrap.sh:84
      Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
      TOKEN_JSON="$(curl --http1.1 -sS -X POST "$TOKEN_URL" \
      quoted
    • low Dangerous commands cmd-privilege scripts/onedrive-setup.sh:28
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      echo "  - Azure CLI: curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash"
      code literal
    • low Exfiltration net-credential-use scripts/onedrive-setup.sh:193
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      drive=$(curl -s "https://graph.microsoft.com/v1.0/me/drive" -H "Authorization: Bearer $token")
      vendor-host

    Files scanned: 11. 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 57/100

    • 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. 7 mutating operations with no state check
    • 40Consistency. Frontmatter name (onedrive) differs from the folder (trendex-onedrive)
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 34 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Execution cost. Instruction body is 2571 tokens
    • 100Progress reporting. Reports progress
    • low 14 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 219: enough signal without eating the budget
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 34 items
    • +4Has examples (13 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 5 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    This appears to be a real OneDrive/SharePoint management skill, but it needs Review because it grants broad persistent cloud-file access and one bootstrap path makes unrelated host-level changes.
    LLM: suspicious (high) · 28 May 2026