The Agent Skills Directory

[SAFE]: The skill's primary function is to read novel project metadata and user-provided chapter summaries to generate promotional text. These operations are confined to local file reading and writing within the project's workspace.
[SAFE]: No network operations, credential usage, or arbitrary command execution patterns were detected in the instructions or configuration files.
[PROMPT_INJECTION]: The skill processes untrusted external data in the form of user-provided plot synopses and finished chapters. While this creates a surface for indirect prompt injection, the risk is mitigated by the skill's limited capabilities, which are restricted to creating markdown files and updating a local YAML index. There is no evidence of high-risk capabilities like network exfiltration or shell access.
Ingestion points: Processes 'completed chapter summaries' and 'user-provided plot synopses' along with local YAML project files.
Boundary markers: None specified in the instructions.
Capability inventory: Writes markdown files to the briefs/ directory and updates the novel-studio/finish.yaml file.
Sanitization: No explicit sanitization or instruction to ignore embedded commands in input data is present.

ns-blurb