The Agent Skills Directory

[SAFE]: A detailed analysis of the skill's instructions, metadata, and workflow confirmed that the agent's operations are limited to read-only research and information synthesis. No evidence of malicious intent, obfuscation, or unauthorized access to sensitive files was found.
[EXTERNAL_DOWNLOADS]: The skill utilizes an external MCP server hosted at mcp.unifapi.com and references installation via the unifapi-agent/agents package. These resources are managed by the skill's author and are used for their intended purpose of providing live data access.
[PROMPT_INJECTION]: The skill ingests untrusted data from public LinkedIn posts and news search results, which presents a surface for indirect prompt injection. \n
Ingestion points: Data retrieved via linkedin/companies/{slug}/posts and news/search. \n
Boundary markers: No explicit delimiters are specified in the prompt templates to separate external data from system instructions. \n
Capability inventory: The skill is restricted to read-only retrieval of public information and lacks the capability to write to the file system or execute shell commands. \n
Sanitization: No specific sanitization or filtering logic is outlined for the external data content. Due to the limited capabilities of the skill, this is classified as a low-risk architectural characteristic.

linkedin-account-research