skill-integrity-auditor@0.1.12
CAUTION· install onlyPublisher 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.
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 deviationsStatic findings
| `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.| `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.gооgleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| `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.| `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.| `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.| 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.| `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.| 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.| `FS` | Local filesystem read / write / delete / chmod |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.…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.…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.…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.Cost to the agent
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%- 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.
- 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.
- Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- 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.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.