The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external search engines (Google, Perplexity, and ChatGPT).
Ingestion points: Data is gathered via snapshot and text commands in SKILL.md (Steps 1, 2, and 3).
Boundary markers: The skill lacks explicit instructions or delimiters to prevent the agent from following instructions found within the scraped content.
Capability inventory: The skill utilizes the Bash tool to execute browse CLI commands.
Sanitization: No sanitization or filtering of the ingested content is performed before processing.
[COMMAND_EXECUTION]: The skill uses the Bash tool to run the browse CLI utility for navigating websites, taking snapshots, and extracting text.
[EXTERNAL_DOWNLOADS]: The skill references the camoufox-js package. It correctly identifies this as a prerequisite and explicitly instructs the agent not to perform automatic installation, instead prompting the user to install it manually.

browse-geo