registry / @papi-ai/server / 0.7.117
@papi-ai/server@0.7.117
PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe flagged credential flow is tied to the PAPI endpoint supplied through configuration, and the statusline changes Claude settings only when explicitly installed. The server’s process execution and network activity fit its stated MCP project-planning purpose; no malicious behavior was established.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The server runs when invoked as a CLI; the statusline runs when invoked, and its settings installation requires --install.
Impact
No unrelated credential forwarding or unrequested agent configuration change was found.
Mechanism
The statusline reads PAPI credentials from explicit arguments, environment variables, or a PAPI entry in .mcp.json, then calls that configured endpoint. Installation adds a statusline command to Claude settings only on request.
AI rationale
The flagged credential flow is tied to the PAPI endpoint supplied through configuration, and the statusline changes Claude settings only when explicitly installed. The server’s process execution and network activity fit its stated MCP project-planning purpose; no malicious behavior was established.
Evidence
.claude/settings.jsonpapi-statusline cache file in the operating-system temporary directory
Network endpoints4
getpapi.aimcp.getpapi.aiapi.getpapi.airegistry.npmjs.org
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes the PAPI server as its main entry and CLI; it declares no install lifecycle scripts.
- The statusline reads a bearer token from PAPI configuration and derives the request origin from that configured PAPI URL.
- The statusline writes Claude settings only when its explicit --install option is passed.
- The server uses git or GitHub CLI to detect a user email, consistent with associating a PAPI project with its user.
- Telemetry is posted to the configured endpoint’s /telemetry route using the PAPI API key.
Evidence against
- The package starts a server and makes network requests, but those actions serve its stated MCP project-planning purpose.
- The statusline sends its bearer token to the configured PAPI endpoint’s /peek route, rather than a fixed unrelated host.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStrings
Source & flagged code
8 flaggeddist/backfill-cycle-metrics.jsView file
271});
L272: import { execFileSync, spawnSync } from "child_process";
L273: function isGitAvailable() {
High
Child Process
Package source references child process execution.
dist/backfill-cycle-metrics.jsView on unpkg · L271dist/index.jsView file
•matchType = previous_version_dangerous_delta
matchedPackage = @papi-ai/server@0.7.106
matchedIdentity = npm:QHBhcGktYWkvc2VydmVy:0.7.106
similarity = 0.400
summary = stored previous version shares package body but lacks this dangerous source file
Critical
Previous Version Dangerous Delta
This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/index.jsView on unpkg32655}
L32656: function powershellQuote(value) {
L32657: return `'${value.replace(/'/g, "''")}'`;
High
Findings
1 Critical5 High4 Medium5 Low
CriticalPrevious Version Dangerous Deltadist/index.js
HighChild Processdist/backfill-cycle-metrics.js
HighShelldist/index.js
HighCredential Redirect Persistencedist/index.js
HighCommand Output Exfiltrationdist/index.js
HighExternal Ai Agent Control Surface Mutationdist/statusline.js
MediumNetwork
MediumEnvironment Vars
MediumShips Build Helperdesign-assets/hooks/frontend-design-guard.sh
MediumStructural Risk Force Deep Review
LowScripts Present
LowWeak Cryptodist/index.js
LowFilesystem
Low
Affected versions and remediation
This report applies to @papi-ai/server@0.7.117.
See all versions of @papi-ai/server for other recorded verdicts.
- Review the evidence and your use of @papi-ai/server@0.7.117 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.