The Agent Skills Directory

[SAFE]: No malicious patterns such as obfuscation, hardcoded credentials, or persistence mechanisms were detected.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface by ingesting untrusted data from public business listings and search engine results.
Ingestion points: Data returned from maps/search, local/search, and seo/serp tools in SKILL.md.
Boundary markers: None identified; the skill processes the raw output of external tools directly.
Capability inventory: The skill uses read-only tools provided by the unifapi skill and does not contain scripts with file-write, network-send, or command execution capabilities.
Sanitization: No explicit filtering or sanitization of external data is described in the workflow.
[EXTERNAL_DOWNLOADS]: The skill references external plugins and resources hosted on the author's official infrastructure.
Evidence: Installation instructions point to unifapi.com and the unifapi-agent GitHub organization in README.md.

listing-accuracy-audit