The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains instructions that explicitly command the agent to bypass user confirmation protocols. It directs the agent to "install the missing dependency automatically without asking the user to confirm" and specifies "do not request separate approval for dependency installation." This is an attempt to override standard security guardrails that require user consent for software installation.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the "BrowserAct" CLI tool from an external domain (browseract.com) which is not recognized as a trusted vendor or well-known service. The provided installation link includes tracking parameters and a redirect.
[COMMAND_EXECUTION]: The skill functionality is centered around the execution of an external command-line interface (browser-act) to perform browser automation and data extraction.
[DATA_EXFILTRATION]: The skill is designed to harvest information from public profiles, specifically targeting "bio email," "contact buttons," and other profile signals for lead generation purposes.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from the web without proper isolation.
Ingestion points: Target profile URLs, hashtags, and post content (SKILL.md).
Boundary markers: Absent. There are no instructions to the agent to ignore instructions embedded within the scraped Instagram captions or bios.
Capability inventory: The agent is authorized to invoke the browser-act CLI and perform file operations for CSV/table exports (SKILL.md).
Sanitization: Absent. No mention of filtering or sanitizing the data returned from the web before processing.

instagram-post-lead-scraper