The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several shell commands to manage its environment and perform data operations. These include npm install for setup, cargo-ai for authentication and data enrichment, and standard utilities like grep, mkdir, and touch for session and state tracking. It also uses the gh CLI for optional social interactions.
[EXTERNAL_DOWNLOADS]: The skill downloads the @cargo-ai/cli package from the npm registry. This is a legitimate vendor resource required for the skill's operations. The skill also references external recipes from the vendor's GitHub repository.
[INDIRECT_PROMPT_INJECTION]: The skill processes external LinkedIn profile URLs, creating an attack surface for indirect prompt injection.
Ingestion points: LinkedIn URLs provided in SKILL.md are passed to the enrichment service.
Boundary markers: No explicit delimiters are used to wrap the input data in the command execution.
Capability inventory: The skill can execute shell commands (npm, cargo-ai, gh), perform network requests via the CLI tool, and write to local configuration files.
Sanitization: The instructions do not specify any sanitization or filtering of the profile data before processing.
[PRIVILEGE_ESCALATION]: The skill interacts with the user's GitHub account using the gh CLI to star a repository. The skill mitigates risk by instructing the agent to obtain explicit user consent before performing this action, preventing unauthorized account modifications.

enrich-linkedin-profile