The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or unauthorized data access patterns were detected. The skill demonstrates safe operational practices by requiring user confirmation for all critical actions.
[PROMPT_INJECTION]: The skill processes freeform user-provided data (scratchpads), which is a characteristic surface for indirect prompt injection. However, the risk is mitigated as the skill is designed to synthesize content for user review rather than execute instructions found within the data. Ingestion points: Scratchpad documents (SKILL.md). Boundary markers: Absent. Capability inventory: Local file system writes and Linear ticket creation (SKILL.md). Sanitization: No automated sanitization is specified. Evaluation: Mandatory user approval steps before any action is taken ensure that the user remains the final authority on the agent's behavior.

blueprint-draft