Skills/ClawHub/skill-integrity-auditor

skill-integrity-auditor@0.1.12

CAUTION· install only

Publisher claims: "Mandatory security audit for **every** Agent Skill that is newly added, installed, imported, updated, or written. Scope of inspection: the full bundle — `SKI..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ambarion · publishing for 192 daysInstalls 1,880Last detonated 42 min ago

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 2026-11-22 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection; Reads credential paths from the home directory; Latin word with Cyrillic or Greek look-alike letters (homoglyph). 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

CRITICAL
Prompt injectionSKILL.md:72 · Prompt injection — known jailbreak technique reference| `LLM` | Prompt manipulation, tool-description poisoning, jailbreak payloads |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Reads credential paths from the home directorySKILL.md:95 · Reads credential paths from the home directory| `FS.ReadSensitive` — read sensitive paths (`~/.ssh`, `~/.aws`, Keychain, browser cookies, `.env`) | 4 | I, R | source |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)SKILL.md:361 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)gооgleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Pipe-to-shell patternSKILL.md:86 · Pipe-to-shell pattern — downloads and immediately executes remote code| `EXE.RemoteFetch` — `curl \| sh` / download-then-exec / fetch-and-run | 4 | I, B | sink |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandSKILL.md:101 · File permission modification command — agent changes file ownership/permissions| `FS.ChmodDangerous` — chmod 777 / privilege widen / SUID bit | 3 | R, I | transform |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsSKILL.md:95 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| `FS.ReadSensitive` — read sensitive paths (`~/.ssh`, `~/.aws`, Keychain, browser cookies, `.env`) | 4 | I, R | source |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:221 · Remote installer piped to shell| T5 | `curl \| sh` / `wget \| bash` / `EXE.RemoteFetch` whose URL is not pinned to a known package registry or a host declared in SKILL.md | **I ≥ 3** |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellSKILL.md:86 · Remote installer piped to shell| `EXE.RemoteFetch` — `curl \| sh` / download-then-exec / fetch-and-run | 4 | I, B | sink |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:221 · Pipe-to-shell pattern — downloads and immediately executes remote code| T5 | `curl \| sh` / `wget \| bash` / `EXE.RemoteFetch` whose URL is not pinned to a known package registry or a host declared in SKILL.md | **I ≥ 3** |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandSKILL.md:68 · File permission modification command — agent changes file ownership/permissions| `FS` | Local filesystem read / write / delete / chmod |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:164 · Remote installer piped to shell…dcoded credential + an `inject into user system` instruction, (d) directive to `curl|sh` from an unverified URL, (e) `LLM.ObfuscatedPrompt` / `LLM.UnicodeSmuggling`, (…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellSKILL.md:350 · Remote installer piped to shell…sSkillWrite` finding as appropriate. 3. **Remote resources.** Patterns such as `curl | sh`, `wget`, `git clone` then `exec`, `pip`/`npm` pointing at non-standard registr…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:350 · Pipe-to-shell pattern — downloads and immediately executes remote code…sSkillWrite` finding as appropriate. 3. **Remote resources.** Patterns such as `curl | sh`, `wget`, `git clone` then `exec`, `pip`/`npm` pointing at non-standard registr…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06

Cost to the agent

Instructions loaded
≈6,866 tok
1 file · 2 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

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ambarion: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Reads credential paths from the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  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. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ambarionPropose a patch to the maintainer