Perplexity Deep Search

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Note

ASI03: Identity and Privilege Abuse

What this means

The skill can use your Perplexity account credentials and may cause API usage charges, especially in research mode.

Why it was flagged

The script reads a Perplexity API key from a specific environment variable or local config file and uses it only as the Authorization header for Perplexity.

Skill content

KEY_FILE="${HOME}/.config/perplexity/api_key" ... PERPLEXITY_API_KEY=$(cat "$KEY_FILE") ... -H "Authorization: Bearer $PERPLEXITY_API_KEY"

Recommendation

Use a dedicated Perplexity API key if possible, keep the key file permission-restricted, and revoke the key if you stop using the skill.

Note

ASI07: Insecure Inter-Agent Communication

What this means

Anything included in the search query is shared with Perplexity for processing.

Why it was flagged

The user’s query is placed into the request payload and sent to the external Perplexity API endpoint, which is consistent with the skill’s search purpose.

Skill content

messages: [ { role: "user", content: $content } ] ... curl -sS "https://api.perplexity.ai/chat/completions"

Recommendation

Avoid placing secrets, private documents, or sensitive personal data in queries unless you are comfortable sending them to Perplexity.