registry  /  pm-claude-skills  /  35.0.0

pm-claude-skills@35.0.0

400 professional Agent Skills (SKILL.md) + subagents + slash commands for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes. It's a CLI, not a library: run `npx pm-claude-skills add --agent <tool>` to install into your AI tool — no `npm install` needed. Or

AI Security Review

scanned 12d ago · by lpm-firewall-ai

No confirmed malicious attack surface. The package is a CLI/MCP bundle for installing and running AI skills; risky primitives are user-invoked and aligned with the advertised functionality.

Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
Explicit user commands such as postinstall banner, add, run, generate, or MCP server startup
Impact
Can modify selected AI-agent skill/rule directories or send provided task content to Anthropic only when the user runs those features
Mechanism
User-invoked skill installation and optional Anthropic API calls
Rationale
Static inspection shows the postinstall is a non-network banner and the higher-risk file/network behaviors occur only through explicit CLI/MCP workflows matching the package purpose. I found no unconsented lifecycle AI-agent control-surface mutation, credential theft, persistence, or malicious exfiltration.
Evidence
package.jsonbin/postinstall.mjsbin/cli.mjsbin/run.mjsbin/generate.mjsbin/lib/anthropic.mjsmcp/server.mjstemplates/pm-launch-agent/orchestrate.shtemplates/pm-sprint-agent/orchestrate.sh
Network endpoints4
mohitagw15856.github.io/pm-claude-skills/github.com/mohitagw15856/pm-claude-skillsraw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/icon.svgapi.anthropic.com/v1/messages

Decision evidence

public snapshot
AI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for block
  • bin/cli.mjs user-invoked add command writes bundled skills/rules into AI agent config directories
  • bin/run.mjs sends user-provided input and bundled skill prompt to Anthropic when ANTHROPIC_API_KEY is set
  • bin/generate.mjs can fetch a user-supplied URL and write a generated SKILL.md
Evidence against
  • package.json postinstall only runs bin/postinstall.mjs banner logic and exits 0; no file or network action
  • bin/cli.mjs has no install-time execution beyond explicit CLI commands; destructive rmSync is limited to replacing selected target skill dirs during user-invoked add
  • mcp/server.mjs is read-only over bundled skills/workflows and stdio JSON-RPC
  • bin/lib/anthropic.mjs only posts to https://api.anthropic.com/v1/messages for explicit run/generate workflows
  • No credential harvesting, persistence, hidden dynamic code execution, or unprompted exfiltration found in inspected entrypoints
Behavioral surface
Source
EnvironmentVarsFilesystemNetwork
Supply chain
HighEntropyStringsUrlStrings
ManifestNo manifest risk signals triggered.
scanned 6 file(s), 41.7 KB of source, external domains: api.anthropic.com, github.com, mohitagw15856.github.io, raw.githubusercontent.com

Source & flagged code

15 flagged · loading source
package.jsonView file
•scripts.postinstall = node bin/postinstall.mjs
High
Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg
•scripts.postinstall = node bin/postinstall.mjs
Medium
Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg
templates/pm-launch-agent/orchestrate.shView file
•path = templates/pm-launch-agent/orchestrate.sh kind = build_helper sizeBytes = 9939 magicHex = [redacted]
Medium
Ships Build Helper

Package ships non-JavaScript build or shell helper files.

templates/pm-launch-agent/orchestrate.shView on unpkg
bin/cli.mjsView file
•matchType = previous_version_dangerous_delta matchedPackage = pm-claude-skills@34.0.0 matchedIdentity = npm:cG0tY2xhdWRlLXNraWxscw:34.0.0 similarity = 0.833 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.

bin/cli.mjsView on unpkg
exports/cline/pm-engineering/load-testing-plan/load-testing-plan.mdView file
206patternName = generic_password severity = medium line = 206 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/cline/pm-engineering/load-testing-plan/load-testing-plan.md

exports/cline/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L206
exports/aider/pm-engineering/load-testing-plan/load-testing-plan.mdView file
206patternName = generic_password severity = medium line = 206 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/aider/pm-engineering/load-testing-plan/load-testing-plan.md

exports/aider/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L206
exports/zed/pm-engineering/load-testing-plan/load-testing-plan.mdView file
206patternName = generic_password severity = medium line = 206 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/zed/pm-engineering/load-testing-plan/load-testing-plan.md

exports/zed/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L206
exports/roo/pm-engineering/load-testing-plan/load-testing-plan.mdView file
206patternName = generic_password severity = medium line = 206 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/roo/pm-engineering/load-testing-plan/load-testing-plan.md

exports/roo/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L206
exports/gemini/pm-engineering/load-testing-plan/GEM_INSTRUCTIONS.mdView file
210patternName = generic_password severity = medium line = 210 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/gemini/pm-engineering/load-testing-plan/GEM_INSTRUCTIONS.md

exports/gemini/pm-engineering/load-testing-plan/GEM_INSTRUCTIONS.mdView on unpkg · L210
exports/kilocode/pm-engineering/load-testing-plan/load-testing-plan.mdView file
206patternName = generic_password severity = medium line = 206 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/kilocode/pm-engineering/load-testing-plan/load-testing-plan.md

exports/kilocode/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L206
exports/windsurf/pm-engineering/load-testing-plan/load-testing-plan.mdView file
211patternName = generic_password severity = medium line = 211 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/windsurf/pm-engineering/load-testing-plan/load-testing-plan.md

exports/windsurf/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L211
exports/obsidian/pm-engineering/load-testing-plan/load-testing-plan.mdView file
213patternName = generic_password severity = medium line = 213 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/obsidian/pm-engineering/load-testing-plan/load-testing-plan.md

exports/obsidian/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L213
exports/chatgpt/pm-engineering/load-testing-plan/SYSTEM_PROMPT.mdView file
206patternName = generic_password severity = medium line = 206 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/chatgpt/pm-engineering/load-testing-plan/SYSTEM_PROMPT.md

exports/chatgpt/pm-engineering/load-testing-plan/SYSTEM_PROMPT.mdView on unpkg · L206
exports/continue/pm-engineering/load-testing-plan/load-testing-plan.mdView file
211patternName = generic_password severity = medium line = 211 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in exports/continue/pm-engineering/load-testing-plan/load-testing-plan.md

exports/continue/pm-engineering/load-testing-plan/load-testing-plan.mdView on unpkg · L211
skills/load-testing-plan/SKILL.mdView file
211patternName = generic_password severity = medium line = 211 matchedText = password...D]',
Medium
Secret Pattern

Hardcoded password in skills/load-testing-plan/SKILL.md

skills/load-testing-plan/SKILL.mdView on unpkg · L211

Findings

1 Critical1 High16 Medium4 Low
CriticalPrevious Version Dangerous Deltabin/cli.mjs
HighInstall Time Lifecycle Scriptspackage.json
MediumAmbiguous Install Lifecycle Scriptpackage.json
MediumNetwork
MediumEnvironment Vars
MediumShips Build Helpertemplates/pm-launch-agent/orchestrate.sh
MediumStructural Risk Force Deep Review
MediumSecret Patternexports/cline/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternexports/aider/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternexports/zed/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternexports/roo/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternexports/gemini/pm-engineering/load-testing-plan/GEM_INSTRUCTIONS.md
MediumSecret Patternexports/kilocode/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternexports/windsurf/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternexports/obsidian/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternexports/chatgpt/pm-engineering/load-testing-plan/SYSTEM_PROMPT.md
MediumSecret Patternexports/continue/pm-engineering/load-testing-plan/load-testing-plan.md
MediumSecret Patternskills/load-testing-plan/SKILL.md
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings