Skills/Claude Code plugins/crowdstrike-falcon-foundry

crowdstrike-falcon-foundry@1.7.1

CAUTION· install only

Publisher claims: "CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API integration, security patterns, and debugging workflows." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher crowdstrike · publishing for 331 daysInstalls 0Last detonated 14 h ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: README links to an external installer; Access to sensitive file paths; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
README links to an external installerREADME.md → https://assets.foundry.crowdstrike.com/cli/latest/foundry_Windows_x86_64.ziphttps://assets.foundry.crowdstrike.com/cli/latest/foundry_Windows_x86_64.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude-plugin/plugin.json:3 · npx invocation of non-well-known package — may execute untrusted code…nd debugging workflows. Swagger 2.0 specs are auto-converted to OpenAPI 3.0 via npx swagger2openapi (requires Node.js; network call to npm registry).", "version": "1.7.1", "au…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandscripts/agy-plugin-swap.sh:68 · Process kill command — agent can terminate processes# Record first, so a kill anywhere below leaves enough behind to undo it.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsskills/e2e-testing/SKILL.md:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files│ ├── .env # Local credentials (git-ignored)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionskills/ai-agents-development/SKILL.md:205 · File type combined with upload action — agent may exfiltrate local data files… Agent Tool References | Fix the entry | | `output_schema must be "output_schema.json"` (or `input_schema …`), or `output schema is required when using JSON format` at deploy | Schema file misnamed, or an inline schema | Name it `output_sc…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Collapsed <details> block carrying instructionsREADME.md:36 · Collapsed <details> block carrying instructions<summary><strong>Install from a local clone</strong> (for development or testing a branch)</summary> ```bash git clone https://github.com/CrowdStrike/foundry-skFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsskills/e2e-testing/SKILL.md:198 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files### 1. Add integration credentials to `.env` and `.env.sample`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/e2e-testing/SKILL.md:99 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandscripts/cursor-plugin-stash.sh:46 · Process kill command — agent can terminate processes# Record the origin first, so a kill right after the move can still be undone.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionskills/ai-agents-development/SKILL.md:95 · File type combined with upload action — agent may exfiltrate local data files…ormat is json`). > **The schema file name is fixed** — it must be `input_schema.json` / `output_schema.json` in the agent directory (a manifest key naming any other file breaks every CLI command in the app; CLI 2.1.2+ renames the file you …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
document.cookie accessskills/ui-development/SKILL.md:171 · document.cookie access — can steal session cookies- **No `allow-same-origin`:** `localStorage`, `sessionStorage`, `document.cookie`, and `indexedDB` throw `SecurityError`. Keep state in memory or a collection.Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packagehooks/foundry-skill-router.sh:195 · npx invocation of non-well-known package — may execute untrusted code# Swagger 2.0 needs converting to a new file, and an npx download can'tFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsskills/e2e-testing/SKILL.md:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files│ ├── .env.sample # Template for other developersFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationskills/security-patterns/SKILL.md:152 · Credential pass-through configuration — agent relays sensitive credentialsfalcon = Alerts() # Do not pass credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
File type combined with upload actionhooks/foundry-cli-guard.sh:143 · File type combined with upload action — agent may exfiltrate local data files# The deploy backend reads only input_schema.json / output_schema.json from theFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsskills/e2e-testing/SKILL.md:66 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files### 3. `.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationskills/functions-development/SKILL.md:290 · Credential pass-through configuration — agent relays sensitive credentialsfalcon = Alerts() # Auth is automatic — do not pass credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Python subprocess execution detectedskills/api-integrations/scripts/adapt_spec_for_foundry.py:66 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=120, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packageskills/e2e-testing/SKILL.md:50 · npx invocation of non-well-known package — may execute untrusted code"test:ui": "npx playwright test --ui",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/debugging-workflows/SKILL.md:192 · npx invocation of non-well-known package — may execute untrusted codeUse `foundry apps validate --no-prompt` to validate the manifest and schemas without deploying. For OpenAPI specs, use `npx @redocly/cli lint` to validate structure locally.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/e2e-testing/SKILL.md:107 · npx invocation of non-well-known package — may execute untrusted codenpx playwright install chromium --with-depsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/e2e-testing/SKILL.md:52 · npx invocation of non-well-known package — may execute untrusted code"test:verbose": "DEBUG=true npx playwright test --reporter=list"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/e2e-testing/SKILL.md:49 · npx invocation of non-well-known package — may execute untrusted code"test": "npx playwright test",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/development-workflow/SKILL.md:237 · npx invocation of non-well-known package — may execute untrusted code- Use `npx @redocly/cli lint` for OpenAPI validation (not Python/Ruby YAML parsers)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/e2e-testing/SKILL.md:51 · npx invocation of non-well-known package — may execute untrusted code"test:debug": "npx playwright test --debug",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/debugging-workflows/SKILL.md:311 · npx invocation of non-well-known package — may execute untrusted code- [ ] Validated OpenAPI specs with `npx @redocly/cli lint` (if applicable)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedskills/development-workflow/scripts/deploy_and_release.py:31 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packageskills/api-integrations/scripts/adapt_spec_for_foundry.py:81 · npx invocation of non-well-known package — may execute untrusted codeprint(" WARNING: npx not found. Install Node.js to enable Swagger 2.0 conversion.")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈60,632 tok
14 files · 80 in bundle

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

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim crowdstrike: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. document.cookie access≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to Claude Code plugins, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim crowdstrikePropose a patch to the maintainer