Context Guardian
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill's requirements, instructions, and included code are consistent with a file-backed context-checkpointing continuity layer and do not request unrelated credentials or network installs.
This skill appears to be what it says: a file-backed continuity layer with a reference Python implementation and tests. Before installing or integrating: 1) Ensure the host supplies the numeric pressure value and a safe workspace root (do not give the skill an unrestricted root like '/'). 2) Constrain guardian_dir to a workspace-controlled path and review which artifact paths may be written or read; the durable state can reference arbitrary files, so avoid putting secrets or host-wide paths in that state. 3) In production, do not rely on the bundled character-based pressure estimator — wire a real host pressure source as the SKILL.md recommends. 4) Review file permissions for the event log and checkpoint files (events.ndjson, task_state.json) to prevent unintended disclosure. 5) Run the included tests in a sandboxed workspace to validate behavior before giving the agent access to your primary project tree.
SkillSpector
SkillSpector findings are pending for this release.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.