The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data from LinkedIn, creating a surface for indirect prompt injection.
Ingestion points: The agent retrieves untrusted content from the web via tools such as linkedin_web_v2_company_posts, linkedin_web_v2_user_posts, and linkedin_web_v2_post_comments as documented in SKILL.md and references/sandbase-api-map.md.
Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between its core instructions and potentially malicious instructions embedded in the fetched LinkedIn content.
Capability inventory: The skill utilizes sandbase_describe_tool and sandbase_call_tool to interact with LinkedIn data via the SandBase API gateway.
Sanitization: The skill does not implement sanitization, filtering, or validation of the retrieved professional content before it is processed by the agent.

linkedin-research