The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown-based instructions and reference templates. No executable scripts (such as Python, JavaScript, or Shell files) are included within the skill package.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied data to generate a customized launch playbook, which represents a standard vulnerability surface for indirect prompt injection.
Ingestion points: Step 1 in SKILL.md collects user inputs including product descriptions, target audience pain points, pricing, and budget details.
Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore embedded instructions within user-provided data.
Capability inventory: The skill has no capabilities beyond text generation. There are no subprocess calls, network operations, or file system writes (other than the standard agent output) requested in the instructions.
Sanitization: No explicit sanitization or validation of user input is implemented.
[SAFE]: A thorough review of the instructions and all reference files (timeline.md, email-templates.md, social-templates.md, outreach.md, metrics-and-antipatterns.md) found no evidence of malicious patterns, such as prompt injection, data exfiltration attempts, obfuscation, or persistence mechanisms.

market-launch