Caveat verdict

skill-blocker

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

Fetches from network AND uses eval/Function

Defines a security gatekeeper role that blocks dangerous operations (rm -rf, curl|sh, eval, credential theft, data exfiltration) before they execute; the skill's content is a defense protocol with no malicious patterns of its own.

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

Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)

LLM05 · LLM06 · ASI05

Capability combination critical

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

LLM05 · LLM06 · ASI05

Capability combination critical

Accesses agent memory/notes AND makes external network calls — may leak personal data

LLM02 · LLM07 · ASI03 · ASI06

Capability combination critical

Accesses system credential store AND makes external network calls

LLM02 · ASI03

Capability combination high

Executes processes AND makes external network calls — may exfiltrate command output

LLM02 · LLM06 · ASI03

Capability combination high

Accesses agent memory AND writes files — may modify agent behavior persistently

LLM01 · LLM06 · ASI01 · ASI06

Capability combination high

Accesses agent memory AND makes external network calls — may leak conversation history

LLM02 · LLM07 · ASI06

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Accesses agent memory/configuration files

agent_memory

Findings (15)

Pattern match critical

Uses eval() — can execute arbitrary code

SKILL.md · frontmatter · eval(

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SKILL.md · frontmatter · curl | sh

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · frontmatter · rm -rf /

Pattern match critical

Pipe to sh — executes piped content as shell commands

SKILL.md · frontmatter · | sh

Pattern match critical

Pipe-to-shell pattern (wget | sh)

SKILL.md · code · wget | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match high

Uses exec() — may execute shell commands

SKILL.md · code · exec(

Pattern match high

References sudo — requests elevated privileges

SKILL.md · code · sudo

Pattern match high

Accesses sensitive system files

SKILL.md · prose · downgraded · /etc/passwd

Pattern match high

Accesses cloud provider credentials

SKILL.md · code · ~/.aws

Pattern match high

Accesses shell history/config

SKILL.md · code · ~/.bash_history

Pattern match high

Accesses .ssh directory

SKILL.md · code · .ssh/

Pattern match medium

References child_process — can spawn system processes

SKILL.md · prose · downgraded · child_process

Pattern match medium

Sets world-executable permissions

SKILL.md · code · chmod 777

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

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.

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