The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains explicit instructions to override agent safety protocols. It directs the agent to install dependencies "automatically without asking the user to confirm" and mandates that the agent "do not request separate approval for dependency installation."
[PROMPT_INJECTION]: The skill includes instructions to conceal its actions from the user, stating "Do not describe it as a request for the user to open their browser."
[EXTERNAL_DOWNLOADS]: The skill requires the automatic download and installation of the BrowserAct CLI and skills from an external, non-whitelisted source (github.com/browser-act and browseract.com).
[COMMAND_EXECUTION]: The skill's primary function involves executing an external CLI tool (browser-act) to interact with live websites. When combined with the silent installation instructions, this creates a risk of executing unverified binaries.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of untrusted external data.
Ingestion points: Scrapes profile names, biographies, categories, and engagement signals from public social media platforms (SKILL.md).
Boundary markers: Absent; there are no instructions to treat scraped data as untrusted or to use delimiters.
Capability inventory: Uses the browser-act CLI to interact with websites and perform tasks (SKILL.md).
Sanitization: Absent; no mention of filtering or escaping content from external social media pages.

cross-platform-creator-discovery