The Agent Skills Directory

[SAFE]: The skill uses a highly structured and transparent methodology for its planning tasks. Analysis found no evidence of hidden code, obfuscated URLs, base64 encoding, credential harvesting, or unauthorized persistence mechanisms.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its automated ingestion and execution capabilities.
Ingestion points: The agent is instructed to read client-provided materials (decks, transcripts, audits) and pull real-time data from external APIs such as Stripe, Shopify, GitHub, and Customer.io.
Boundary markers: The instructions lack directives to wrap ingested data in delimiters or to ignore potential instructions embedded within those source materials.
Capability inventory: The skill has significant capabilities, including the ability to write to GitHub repositories, send lifecycle emails via Customer.io, and manage social media posts through Typefully.
Sanitization: There are no explicit requirements for the agent to sanitize or validate external content before it is interpolated into the final deliverables or passed to secondary tool actions.

marketing-plan