The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses dynamic context injection (!command) within SKILL.md to execute shell commands (command -v, opencli doctor) to verify the environment when the skill is loaded.
[EXTERNAL_DOWNLOADS]: The skill directs the user to install a third-party Node.js package (@jackwener/opencli) which is hosted on a public registry and authored by an individual contributor outside the trusted vendor list.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it retrieves and processes LinkedIn posts and job descriptions which could contain instructions designed to manipulate the agent's behavior.
Ingestion points: Untrusted content enters the context via opencli linkedin timeline and opencli linkedin search outputs as described in SKILL.md.
Boundary markers: Absent; the skill does not use specific delimiters or instructions to prevent the agent from obeying instructions embedded in the external data.
Capability inventory: The agent has the capability to execute shell commands through the opencli tool.
Sanitization: No sanitization or validation of the retrieved LinkedIn content is implemented before processing.

linkedin-reader