The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The skill follows standard practices for local data processing and knowledge management.
[DATA_EXFILTRATION]: The skill connects to a local service at http://localhost:6363 and writes to a local .agent-memory directory. These operations are restricted to the local environment and do not transmit data to external third-party domains.
[PROMPT_INJECTION]: The skill processes user-supplied observations to generate speculative knowledge. While this constitutes an attack surface for indirect prompt injection, the implementation focuses on structured knowledge extraction and does not contain instructions to override system safety protocols.

infer