@mnemom/mnemom@0.17.29
Transparent AI agent tracing
AI Security Review
scanned 6h ago · by lpm-firewall-aiThe remote-control path forwards an existing Anthropic API key to a gateway, creating credential exposure dependent on gateway selection. Source inspection did not establish an unrelated recipient, so this warrants a warning rather than a block.
Decision evidence
public snapshot- The explicit remote-control launch starts a local proxy.
- The proxy routes Anthropic message requests to a gateway URL supplied through its environment.
- For non-subscription requests, it puts the Anthropic API key in the gateway request’s x-api-key header.
- The Slack reply handler passes the bot token and caller-supplied channel and text to postMessage.
- The routing handler ignores bot events and events missing a user, channel, or timestamp.
- The proxy removes the OAuth bearer from non-subscription requests.
- The inspected source does not establish that the gateway URL is unrestricted or controlled by an unrelated recipient.
Source & flagged code
5 flagged · loading sourceA single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/rc-proxy.mjsView on unpkg · L87Findings
Affected versions and remediation
This report applies to @mnemom/mnemom@0.17.29.
See all versions of @mnemom/mnemom for other recorded verdicts.
- Review the evidence and your use of @mnemom/mnemom@0.17.29 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.