Skillv1.0.1

ClawScan security

Maven Smart System Ai (palantir integration) · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

ReviewMar 14, 2026, 12:35 PM

Verdict: Review
Confidence: medium
Model: gpt-5-mini
Summary: The skill's code and SKILL.md are coherent with a Palantir MSS integration (and perform highly sensitive actions), but registry metadata omits declared credentials and the skill persistently writes API keys to a .env file — these mismatches and persistence behaviors warrant caution before installing.
Guidance: This package contains real-world targeting functionality and will call your Palantir MSS endpoint using MSS_API_KEY and MSS_API_ENDPOINT. Before installing: 1) Verify the publisher and source — there is no homepage or known owner. 2) Do not provide a high-privilege/production API key for testing; create a least-privilege, audit-enabled test key instead. 3) Inspect the code locally (mss_client.py, setup_env.py, and the POST/PATCH callers) and confirm you trust the endpoint URL; setup_env.py writes credentials in plaintext to a .env at the repo root and can overwrite existing MSS entries. 4) Ensure your agent runtime enforces the SKILL.md safety confirmations (the scripts themselves will execute actions if invoked). 5) If you need stronger assurance, request provenance (signed release, VCS repo, maintainer identity) or run the skill in an isolated environment without network access until validated.

Review Dimensions

Purpose & Capability: concernThe SKILL.md and bundled scripts clearly implement Palantir MSS functionality (target lookup, SIGINT fetch, CDE, assigning strike assets, status changes). That matches the declared purpose. However, the registry metadata at the top of the submission lists 'Required env vars: none' and 'Primary credential: none', while SKILL.md and the code require MSS_API_KEY and MSS_API_ENDPOINT — an important metadata mismatch that could hide required credentials from reviewers.
Instruction Scope: noteSKILL.md instructs the agent to check for MSS_API_KEY and to call initialize_config to write a .env file if missing; it also requires explicit operator confirmation (per the 'Safety Protocol') before actions that move targets toward engagement. This scope is consistent with the stated purpose. However, confirmation is a procedural requirement in SKILL.md only — it is not enforced by the scripts themselves (the scripts will perform POST/PATCH calls if invoked). The agent runtime must reliably prompt and block potentially harmful actions; otherwise the skill can perform impactful operations.
Install Mechanism: okNo external install script or remote download is present; the package is instruction+scripts only. requirements.txt lists common Python libs (requests, python-dotenv). No high-risk remote installs or obscure URLs were found.
Credentials: concernSKILL.md and mss_client.py legitimately require MSS_API_KEY and MSS_API_ENDPOINT. But the registry metadata omitted these required env vars — an incoherence. The setup_env.py writes the API key and endpoint into a plaintext .env file at the repository root, which will persist sensitive credentials on disk and may overwrite or alter an existing .env; this persistence is disproportionate unless the operator expects local storage. No other unrelated credentials are requested.
Persistence & Privilege: noteThe skill does not request 'always: true' or other elevated platform privileges. It does, however, persistently store the API key and endpoint in a .env file and will make authenticated API calls (GET/POST/PATCH) to the configured endpoint. That persistent storage is normal for a client integration but increases the blast radius if the workspace is shared or backups/uploaded.