The Agent Skills Directory

[SAFE]: The skill provides structured guidance and examples for literary market research. The instructions are transparent and aligned with the skill's stated purpose, with no evidence of obfuscation, remote code execution, or persistence mechanisms.
[PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection through the ingestion of untrusted book metadata.
Ingestion points: User-provided manuscript details, including titles, themes, and protagonist descriptions.
Boundary markers: None; the skill does not specify the use of delimiters or provide instructions to treat the data as inert content.
Capability inventory: The skill requires permissions for web:search and file:read tools.
Sanitization: No sanitization or validation protocols are described for processing the external book information.

comp-title-finder