deep-digger@1.1.0
BLOCKED· install onlyPublisher claims: "Catch that bug: Evidence-gated root cause investigation & controlled falsification for AI agents" Observed in sandbox: reads credential files, sends data to fd12:ea5f:789c:1:d000:1c1:d8f4:2be4, 10.244.43.228, www.skills.sh.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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 (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-08 and scored it 30/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Summary: reads credential files, sends data to fd12:ea5f:789c:1:d000:1c1:d8f4:2be4, 10.244.43.228, www.skills.sh.
Behavior trace
Honeypot run · 7 s · 2 scenariosStatic findings
subprocess.run(["git", "rev-parse", "--is-inside-work-tree"], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.console.log('[Deep Digger] Running post-installation configuration...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.// 1. Attempt npx / bunx skills add if online and registry tool is availableFix: Pin versions and sources; vendor anything fetched at install time.Skills Registry: npx skills add imMamdouhaboammar/deep-diggerFix: Pin versions and sources; vendor anything fetched at install time.result = subprocess.run(argv, shell=False, timeout=timeout,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p_start = subprocess.run(start_cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p_run = subprocess.run(bisect_run_cmd, capture_output=True, text=True, timeout=args.timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "bisect", "reset"], capture_output=True)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
No advisories in OSV for deep-digger@1.1.0 as of 6d ago. This is the package itself, not its dependencies.
What would make this Verified
50 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%An override rule (credential_read_plus_egress) caps this verdict regardless of the score. The first item below has to go before anything else counts.
- 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.
- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Unclaimed publisher≈ +8 on the totalClaim immamdouhaboammar: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.