The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external LinkedIn sources (such as post content, comments, and mentions) which could contain malicious instructions.
Ingestion points: Data is retrieved from the LinkedIn REST API endpoints (e.g., /linkedin-post-statistics) and engagement tools like linkedin_list_mentionables described in SKILL.md.
Capability inventory: The agent has the ability to perform actions on the user's behalf, including linkedin_create_comment and linkedin_create_reshare as defined in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when handling the external data.
Sanitization: No explicit sanitization or validation of the retrieved LinkedIn content is performed before processing.

linkedin-analytics