Skills/npm/agentreplayer

agentreplayer@0.11.6

CAUTION· install only

Publisher claims: "Turn any AI coding agent session (Claude Code, Codex, Gemini CLI, OpenCode, Cline, Roo, Copilot CLI, Aider, …) into a shareable, video-like HTML replay with cost stats and secret redaction." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher dorywoof · publishing for 3 daysInstalls 1,387Last detonated 32 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 0.11.5

vet-skills diff agentreplayer 0.11.5 0.11.6

In the sandbox, this version reached for nothing 0.11.5 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Says it makes no network calls; the code sends requests to an outside host; Hidden zero-width characters detected; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sfilesystemread ~/.claude/projects · ~/.codex/sessions · ~/.gemini/tmp · ~/.qwen/projects · ~/.local/share/opencode/storage/session · ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/tasks outside project
0.1sprocessexited 1: agentreplayer: no agent sessions found on this machine. Pass a log file path instead.
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.6sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.8sprocess8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.8sprocessscript backend runs setup only
0.8sprocessscript backend runs setup only
0.8sprocessno install scripts to re-run

Static findings

HIGH
Says it makes no network calls; the code sends requests to an outside hostsrc/share.js:35 · Says it makes no network calls; the code sends requests to an outside host (stated in its description)const res = await fetch('https://api.github.com/gists', {Fix: Declare and request only the permissions the task needs.
AST02
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/insights.js:317 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…: ''}. Ask the agent to filter (head, grep, a quiet flag, a narrower query), or add that rule to CLAUDE.md / AGENTS.md.`, }); } const worstLoop = R.loops[0]; if (worstLoop) { const lo…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageskills/replay/SKILL.md:5 · npx invocation of non-well-known package — may execute untrusted codeallowed-tools: Bash(npx -y agentreplayer*), Bash(npx agentreplayer*)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/agentreplayer.js:278 · npx invocation of non-well-known package — may execute untrusted code'setup writes the path of this program into Claude Code settings, and npx runs it from a temporary cache.\n' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/agentreplayer.js:176 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(dim('\n The status line hasn\'t run yet. Restart Claude Code and send one message.'));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Hidden zero-width characters detectedsrc/parsers/agents.js:36 · Hidden zero-width characters detected — may conceal contentreturn JSON.parse(fs.readFileSync(f, 'utf8').replace(/^/, ''));Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detectedsrc/util.js:63 · Hidden zero-width characters detected — may conceal contentconst raw = fs.readFileSync(file, 'utf8').replace(/^/, '');Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
npx invocation of non-well-known packageskills/replay/SKILL.md:20 · npx invocation of non-well-known package — may execute untrusted codenpx -y agentreplayer@latest --agent <agent> -o agentreplayer.htmlFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,005 tok
1 file · 25 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/tasks.
  2. Unclaimed publisher≈ +8 on the totalClaim dorywoof: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  4. Says it makes no network calls; the code sends requests to an outside host≈ +4 on the totalDeclare and request only the permissions the task needs.
  5. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  6. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dorywoofPropose a patch to the maintainer