agently-session-memo

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructional content and does not contain executable code or malicious logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes loading session data from external JSON or YAML files, which is a potential data ingestion point. Ingestion points: load_json_session() and load_yaml_session() methods in references/serialization-and-restore.md. Boundary markers: CHAT SESSION MEMO header mentioned in references/resize-and-memo.md. Capability inventory: Session lifecycle and context window management. Sanitization: The documentation recommends validating restored state before use.
  • [EXTERNAL_DOWNLOADS]: References to external source code and documentation are limited to the official Agently GitHub repository and documentation site. Evidence: URLs in references/source-map.md point to github.com/AgentEra/Agently and agently.tech. These are trusted vendor resources and are documented neutrally.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 05:52 PM