Back to skill
Skillv1.0.0
ClawScan security
LinkdAPI · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
SuspiciousMar 11, 2026, 11:25 AM
- Verdict
- suspicious
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill claims to provide a complete LinkdAPI integration (including SDKs and authentication) and shows runtime instructions that require LINKDAPI_KEY, but the package is instruction-only, ships no SDKs, and the registry metadata does not declare the required credential — these mismatches are suspicious and warrant verification before installing.
- Guidance
- This package is inconsistent: its docs require an API key (LINKDAPI_KEY) and claim included SDKs, but the distributed bundle provides only documentation (no SDKs) and the registry metadata doesn't list the API key or a homepage. Before installing: 1) Verify the publisher and the linkdapi.com service independently (do not trust only these files). 2) Do not paste your LINKDAPI_KEY (or any secret) into the agent until you confirm the skill's source and that the registry metadata has been corrected to declare the env var/primary credential. 3) Ask the publisher to either include the SDK code or remove the SDK claim, and update the registry to declare LINKDAPI_KEY as required/primary credential. 4) Consider privacy/ToS risk: LinkdAPI appears to scrape LinkedIn data (emails/phones may be returned) — ensure you are allowed to use such data. If you can't verify the publisher or the missing metadata is not fixed, avoid installing or supplying credentials.
Review Dimensions
- Purpose & Capability
- concernThe skill's name/description promise 'Python/Node.js/Go SDKs, authentication' yet the package contains no code files or SDKs (instruction-only). The SKILL.md documents an API key (LINKDAPI_KEY) and a third-party base URL (https://linkdapi.com), but the registry metadata lists no required env vars or primary credential and there is no homepage/source URL — these are incoherent.
- Instruction Scope
- noteSKILL.md contains detailed, scoped instructions for calling LinkdAPI endpoints and an explicit example using LINKDAPI_KEY; it does not ask the agent to read unrelated local files or exfiltrate data to unknown endpoints. However it instructs the agent to 'Always use this skill for ANY LinkedIn data task', which is a broad directive that may cause the agent to overuse the skill autonomously.
- Install Mechanism
- okThere is no install spec and no code is written to disk (instruction-only), which minimizes install-time risk. The references are local docs only.
- Credentials
- concernThe SKILL.md clearly requires an API key via LINKDAPI_KEY and specifies the auth header X-linkdapi-apikey, but the registry metadata did not declare any required env vars or a primary credential. That mismatch is a red flag (the skill expects a secret but doesn't declare it), and the owner/source/homepage are missing which makes it harder to validate the credential recipient.
- Persistence & Privilege
- okThe skill does not request 'always: true' and uses default agent-invocation behavior. It does not attempt to modify other skills or system-wide config in the provided content.