The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions and markdown templates. It does not include any scripts, executable files, or package dependencies.
[SAFE]: No malicious patterns, such as direct prompt injection, data exfiltration, or obfuscation, were identified. The skill is limited to content generation within the agent's standard operating environment.
[PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest data from user prompts and external research results into its context. 1. Ingestion points: User input from the feature brief/idea and external content retrieved during the 'Research' step. 2. Boundary markers: Absent; there are no delimiters used to isolate external content from the skill's primary instructions. 3. Capability inventory: The skill is limited to generating structured markdown text output. 4. Sanitization: None specified for external content.

prd-writer