Caveat verdict
universal-skills-manager
Skill manager that discovers and installs AI skills from multiple registries (SkillsMP, SkillHub, ClawHub) with an optional API key — legitimate coordination tool with no evidence of malicious behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (13)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · prose · downgraded · curl -fsSL https://raw.githubusercontent.com/jacob-bd/universal-skills-manager/m
Pipe to sh — executes piped content as shell commands
SKILL.md · prose · downgraded · | sh
Recursive delete from root or home — destructive command
SKILL.md · prose · downgraded · rm -rf /
Pipe to python — executes piped content as Python code
scripts/scan_skill.py · prose · downgraded · |python
Accesses sensitive system files
scripts/scan_skill.py · prose · downgraded · /etc/passwd
Attempts to modify skills or system prompts
scripts/validate_frontmatter.py · prose · downgraded · Replace SKILL.md
subprocess execution — runs system commands from Python
scripts/install_skill.py · prose · downgraded · subprocess.run(
Accesses .ssh directory
scripts/scan_skill.py · prose · downgraded · .ssh/
Python urllib.request — network access
scripts/install_skill.py · prose · downgraded · urllib.request
Popular HTTP library — network access
scripts/install_skill.py · prose · downgraded · got
Python shutil file operation — copies/moves/deletes files
scripts/install_skill.py · prose · downgraded · shutil.rmtree(
References webhook/callback URL
scripts/scan_skill.py · prose · downgraded · WEBHOOK_URL
Base64 encoding/decoding
scripts/scan_skill.py · prose · downgraded · base64-encode
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.