@getpromptly/cli@0.2.10
Developer prompt analytics CLI - capture and review AI coding sessions
AI Security Review
scanned 25d ago · by lpm-firewall-aiSource inspection found first-party agent configuration and skill setup capabilities triggered through explicit CLI commands, including confirmation before skill installation and generated changes. No automatic install hook or concrete malicious behavior was established, so this warrants a warning for agent capability rather than a publish block.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user invokes the relevant setup or apply command.
Impact
These changes affect later agent behavior by providing Promptly tracking instructions or workflow skills; the inspected evidence does not establish covert mutation or malicious execution.
Mechanism
The CLI can update project MCP configuration, agent instruction files, and skill files to enable Promptly session tracking or generated workflows.
AI rationale
Source inspection found first-party agent configuration and skill setup capabilities triggered through explicit CLI commands, including confirmation before skill installation and generated changes. No automatic install hook or concrete malicious behavior was established, so this warrants a warning for agent capability rather than a publish block.
Evidence
package.jsondist/commands/autoprompt.jsdist/commands/init.jsdist/commands/optimize-apply.jsdist/commands/skill.jsdist/commands/statusline.js.mcp.json.claude/skills/
Decision evidence
public snapshotAI called this Suspicious at 84.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest exposes a CLI and has no install lifecycle hook.
- The auto-prompt command locates project instruction files for agent setup.
- Init reads and updates the project MCP configuration.
- The apply command can generate a Claude skill from a workflow sequence.
- The skill command checks agent configuration and prompts before installing the tracking skill.
- Statusline reads Claude settings; the inspected excerpt does not show a write.
- The auto-prompt setup is an explicit interactive operation.
- Init asks before installing the tracking skill.
Evidence against
- The manifest has no preinstall, install, or postinstall lifecycle hook.
- The inspected skill installation and generated-change paths are explicit CLI operations with confirmation prompts.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStrings
Source & flagged code
4 flaggeddist/commands/login.jsView file
27package = @getpromptly/cli; repositoryIdentity = promptly; dependency = open
L27: try {
L28: const open = (await import("open")).default;
L29: await open(verificationUrl);
High
Copied Package Dependency Bridge
Package metadata claims a different repository identity while copied source loads a runtime dependency bridge.
dist/commands/login.jsView on unpkg · L27dist/commands/skill.jsView file
•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation.
n iscodexconfigured() {
const configpath = path.join(os.homedir(), ".codex", "config.toml");
try {
if (!fs.existssync(configpath))
return false;
const content = fs.readfilesync(configpath, "utf-8");
return content.includes("[mcp_servers.promptly]");
}
catch {
return false;
}
}
export function isgeminiinstalled() {
try {
execsync("gemini --version", { stdio: "ignore" });
return true;
}
catch {
return false;
}
}
export function isgeminiconfigured() {
const configpath = path.join(os.homedir(), ".gemini", "settings.json");
try {
if (!fs.existssync(configpath))
High
Findings
3 High4 Medium5 Low
HighCopied Package Dependency Bridgedist/commands/login.js
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/commands/skill.js
HighPrevious Version Dangerous Deltadist/commands/review-pr.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
MediumSuspicious Lifecycle Evidencepackage.json
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowTelemetry
LowUrl Strings
Affected versions and remediation
This report applies to @getpromptly/cli@0.2.10.
See all versions of @getpromptly/cli for other recorded verdicts.
- Review the evidence and your use of @getpromptly/cli@0.2.10 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.