Caveat verdict

skill-install-guardian

security-audit-tools

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Writes files AND executes processes

Skill install guardian that inspects third-party skills for security risks before installation; purely instructional with red-flag detection guidance and no malicious behavior in the content itself.

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.

0
security
70
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Writes files AND executes processes — may drop and execute malicious scripts

LLM05 · LLM06 · ASI05

Capability combination critical

Reads files AND uses eval/Function — may execute locally stored payloads

LLM05 · LLM06 · ASI05

Capability combination high

Installs packages AND executes processes — opaque dependency chain with execution

LLM03 · ASI04

Capability combination medium

Both reads and writes files — verify scope is limited to intended directories

LLM06 · ASI02

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (10)

Pattern match high

Pipe to bash — executes piped content as shell commands

findings-catalog.md · prose · downgraded · |bash

Pattern match high

Pipe to sh — executes piped content as shell commands

findings-catalog.md · prose · downgraded · |sh

Pattern match high

References child_process — can spawn system processes

SKILL.md · code · child_process

Pattern match high

Uses eval() — can execute arbitrary code

findings-catalog.md · prose · downgraded · eval(

Pattern match high

Dynamic Function constructor — equivalent to eval()

README.md · prose · downgraded · new Function(

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Accesses system credential store

findings-catalog.md · prose · downgraded · keychain

Pattern match medium

Uses exec() — may execute shell commands

tools/audit-source-code.sh · prose · downgraded · exec(

Pattern match medium

Uses spawn() — can execute external programs

tools/audit-source-code.sh · prose · downgraded · spawn(

Pattern match low

Popular HTTP library — network access

tools/quick_scan.py · prose · downgraded · axios

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/C/D/E). 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.

file_readfile_writeprocess_execdynamic_evalpackage_install
Check another skill Browse the registry Auditing your own skills or configs? Use the API