Skillv1.0.0

ClawScan security

botlearn-twitter-intel · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

ReviewMar 1, 2026, 7:32 AM

Verdict: Review
Confidence: medium
Model: gpt-5-mini
Summary: The skill's instructions describe real-time Twitter/X monitoring and use of authenticated API endpoints, but the package declares no credentials, environment variables, or install requirements — this mismatch is unexplained and worth caution.
Guidance: This skill's documentation shows how to use Twitter/X APIs (including streaming and full-archive access) and gives a detailed analyst workflow, but it does not declare how it will authenticate to Twitter. Before installing or enabling this skill: (1) ask the publisher how authentication is provided and whether the skill expects you to supply API credentials (Bearer token, API key/secret, or elevated Academic/Pro access); (2) confirm where and how the skill will make network calls and whether it will store or transmit collected tweets outside your environment; (3) if you must provide credentials, prefer using short-lived, least-privilege tokens and ensure the skill uses a secure secret store rather than embedding secrets in plaintext; (4) if your platform provides a vetted Twitter connector, verify the skill is explicitly configured to use that connector. The mismatch between required capabilities and declared credentials is the main red flag — it may be an oversight, but treat it as unresolved until clarified.

Review Dimensions

Purpose & Capability: concernThe skill's stated purpose is live Twitter/X monitoring (search, filtered stream, full-archive) and bot detection, which normally requires authenticated access (API keys/tokens) and possibly elevated API tiers. The manifest and SKILL.md reference v2 endpoints and rate limits, yet the skill declares no required environment variables or primary credential. That is disproportionate: a Twitter-intel skill should at minimum declare a bearer token or instructions to use a platform-provided connector.
Instruction Scope: noteSKILL.md provides detailed runtime instructions: building queries, fetching tweets, retrieving threads (conversation_id), running bot heuristics, and synthesizing briefings. Those instructions are scoped to the stated purpose and do not ask the agent to read unrelated system files or exfiltrate secrets. However they assume the agent can execute API calls and paginate/stream results without specifying how authentication or network access are provided.
Install Mechanism: okThis is an instruction-only skill with no install spec and no code files to execute — low disk/write risk. Files are documentation (knowledge, strategies, tests). No remote downloads or install scripts are present.
Credentials: concernThe skill requires access to Twitter API endpoints in its instructions (Recent Search, Filtered Stream, Full-Archive) but declares zero required env vars or credentials. Typical required variables (e.g., TWITTER_BEARER_TOKEN, TWITTER_API_KEY/SECRET, or a platform connector config) are missing. This gap is a proportionality/integrity issue: the skill either omits declaring needed sensitive credentials or expects implicit platform-level credentials (not documented).
Persistence & Privilege: okThe skill does not request 'always: true', does not declare system config paths, and does not modify other skills. Autonomous invocation is allowed by default, which is normal; there are no extra persistence/privilege flags in the manifest.