The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from external enrichment sources without sanitization or boundary markers.
Ingestion points: External data enters the context through tool calls like find-and-enrich-company, find-and-enrich-contacts-at-company, and ask-question-about-accounts mentioned in SKILL.md.
Boundary markers: There are no delimiters or instructions provided to the agent to treat the fetched enrichment data purely as data and ignore any embedded commands.
Capability inventory: The skill leverages the agent's ability to synthesize new text (like the {{custom_hook}}) based on these external inputs.
Sanitization: No mechanisms are defined to sanitize or validate the content of the enrichment data before it is interpolated into the final outreach messages.

template-personalizer