The Agent Skills Directory

[SAFE]: The skill follows security best practices by instructing the agent to redact sensitive information before saving the output document. No evidence of malicious intent, data exfiltration, or unauthorized command execution was found.
[INDIRECT_PROMPT_INJECTION]: The skill ingests conversation history to generate summaries, which is a potential surface for indirect prompt injection. Ingestion points: Current conversation history processed during handoff generation. Boundary markers: Not explicitly defined in the prompt instructions. Capability inventory: The skill is limited to file-write operations for the handoff document. Sanitization: The prompt explicitly mandates redacting API keys, passwords, and PII.

light-handoff