influship-api-mcp@0.19.0
The official MCP Server for the Influship API
AI Security Review
scanned 22d ago · by lpm-firewall-aiThe active remote execution path forwards service credentials to an unrestricted configurable destination, meeting the warning threshold for conditional credential exposure. No separate block-eligible malicious behavior was established.
Decision evidence
public snapshot- The remote handler selects an unrestricted execution endpoint through CODE_MODE_ENDPOINT_URL.
- The handler obtains the Influship API key from the environment or initialized client and merges it into forwarded credentials.
- The handler sends those credentials in a POST request header; the ES module implements the same behavior.
- The code tool is enabled by default with remote execution, and invoking it activates credential forwarding.
- No automatic install lifecycle hook or runtime self-dependency was found.
- Remote execution serves the package's API tooling purpose; no covert recipient or malicious intent was established.
Source & flagged code
10 flagged · loading sourceSource file is highly similar to a previously finalized malicious package; route for source-aware review.
instructions.jsView on unpkgPackage source references dynamic require/import behavior.
instructions.jsView on unpkg · L7Findings
Affected versions and remediation
This report applies to influship-api-mcp@0.19.0.
See all versions of influship-api-mcp for other recorded verdicts.
- Review the evidence and your use of influship-api-mcp@0.19.0 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.