The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it requires the agent to ingest and act upon data from untrusted external sources.
Ingestion points: Workflow Step 2 in SKILL.md instructs the agent to research external recipient signals from sources such as company pages, filings, job posts, and public writing.
Boundary markers: The skill does not prescribe the use of delimiters, XML tags, or unique framing markers to isolate researched data from the agent's core instructions.
Capability inventory: The skill leverages the agent's ability to read external content and generate send-ready professional communications, providing a pathway for external content to influence output.
Sanitization: The instructions do not define requirements for sanitizing, escaping, or filtering the content retrieved from external sources before it is processed by the agent.

cold-outreach