The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from multiple sources to influence its output.
Ingestion points: The agent is instructed to read spec.md, design.md, visual.md, and scan the broader codebase to gather context.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the ingested documents are defined.
Capability inventory: The skill possesses file-writing capabilities, specifically creating or updating docs/<feature-name>/issues.json and docs/index.json.
Sanitization: There is no evidence of sanitization or validation logic to prevent malicious instructions embedded in the input markdown files from appearing in the generated task list.

simple-tasks