The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package from the NPM registry and potentially fetches additional skills from GitHub using npx skills add.- [COMMAND_EXECUTION]: The skill executes various shell commands, including cargo-ai for data orchestration, npm for package management, and gh for GitHub API interactions.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external company websites and job listings to generate briefings.
Ingestion points: Content is retrieved from arbitrary domains via parallel.extract and job search results via theirStack.searchJobs (SKILL.md).
Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard potential instructions embedded within the retrieved website content.
Capability inventory: The skill has access to command execution (cargo-ai, gh, npm), file system access (reading plugin configurations), and network operations.
Sanitization: The skill does not implement sanitization, filtering, or validation of the external content before it is processed by the agent.- [DATA_EXFILTRATION]: The skill sends session metadata, including a session ID and title, to the vendor's infrastructure using the cargo-ai workspaceManagement session upsert command.

research-account