The Agent Skills Directory

[SAFE]: No security issues detected. The skill focuses on providing instructions for writing marketing copy and includes templates for various page types.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file (.claude/product-marketing-context.md) to provide context for copywriting tasks. While this presents an attack surface for instructions embedded in external data, the skill lacks the capabilities to perform dangerous actions, such as network requests or file system modifications, that could be exploited.
Ingestion points: .claude/product-marketing-context.md (referenced in SKILL.md)
Boundary markers: Absent
Capability inventory: None detected across all scripts (text generation only)
Sanitization: Absent

copywriting