Caveat verdict

pinchtab

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

Receives external input AND uses eval

Browser automation skill using the PinchTab CLI to navigate, interact with elements, and extract data from web pages; dynamic_eval via the pinchtab eval command is used for legitimate UI automation with user direction, not hidden code execution.

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
80
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

Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)

LLM01 · LLM05 · ASI01 · ASI05

Capability combination critical

Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)

LLM05 · ASI05 · ASI10

Findings (4)

Pattern match critical

Uses eval() — can execute arbitrary code

references/agent-optimization.md · code · eval (

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/env.md · code · http://192.168.1.50

Pattern match medium

Base64 encoding/decoding

references/api.md · code · base64-encode

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · Got

Permissions & capabilities

Requires 1 system binary.

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