1

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Note

ASI03: Identity and Privilege Abuse

What this means

Anyone or any agent using this token may be able to access or modify MaybeAI spreadsheet documents allowed by that token.

Why it was flagged

The skill requires a bearer token for the MaybeAI API, which gives the agent delegated access to the user's MaybeAI spreadsheet operations.

Skill content

requires:
  env:
    - MAYBEAI_API_TOKEN
...
Authorization: Bearer <MAYBEAI_API_TOKEN>

Recommendation

Use a revocable, least-privilege token if MaybeAI supports it, keep it out of logs and chat history, and rotate it if exposed.

Note

ASI07: Insecure Inter-Agent Communication

What this means

Spreadsheet contents may leave the local machine and be stored or processed by MaybeAI.

Why it was flagged

Spreadsheet files are uploaded to the disclosed MaybeAI backend. This is expected for the skill, but it is a sensitive external data flow.

Skill content

BASE_URL="https://play-be.omnimcp.ai"
...
curl -s -X POST "$BASE_URL/api/v1/excel/upload" \
  -F "file=@./sample.xlsx"

Recommendation

Upload only files intended for MaybeAI processing, review MaybeAI's privacy/retention terms for sensitive spreadsheets, and treat document IDs and exported files as sensitive.

Note

ASI02: Tool Misuse and Exploitation

What this means

A mistaken command or unreviewed script run could modify or delete spreadsheet content in the user's MaybeAI account.

Why it was flagged

The skill intentionally exposes spreadsheet mutation and deletion endpoints. They fit the stated lifecycle-management purpose, but wrong document IDs, ranges, or sheets could cause data loss.

Skill content

"Delete rows 3–5" | `POST /api/v1/excel/delete_rows`
...
"Delete File" | `POST /api/v1/excel/delete_file`

Recommendation

Confirm the target document, worksheet, and range before destructive edits, keep backups or versions, and avoid running full example scripts on important files without reviewing each API call.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Users may need local tooling before running the scripts, and package installation should be done carefully.

Why it was flagged

The skill's examples depend on local command-line tools and package-manager installation. This is normal for curl-based API examples, but users should install dependencies from trusted sources.

Skill content

> **Requires**: `curl` and `jq`. Install jq with `brew install jq` (macOS) or `apt install jq` (Linux).

Recommendation

Install curl/jq from trusted system package managers and review shell scripts before running them.