Security audit
Security checks for vulnerabilities and agentic risk
The skill does not show clear malware, but it needs review because it asks for file-writing and command authority while its trigger scope and API behavior are unclear.
Install only if you intend to let an agent modify canvas files and run local command-line tooling for that purpose. Before using it on important data, require explicit target paths, review diffs before writes, keep backups, and clarify whether any API-key-backed or network service features are actually needed.
The activation text is extremely broad, describing general efficiency, automation, and workflow optimization use cases rather than canvas-specific tasks. In agent systems, overly broad triggering is dangerous because it can cause the skill to activate for unrelated requests and gain access to powerful tools like read, write, and exec in situations the user did not intend.
The skill documents merge, repair, rollback, checkpoint recovery, and command-execution behavior that can modify files or overwrite user state, but it does not prominently require confirmation, backups, or dry-run behavior before destructive changes. In the context of a skill with read/write/exec tools, this increases the risk of accidental data loss or unauthorized modification of user content.
The API Key configuration section states that the skill does not require any additional API key and that batch/layout features run locally. Later FAQ content says some features do require platform API keys, which directly contradicts the earlier intent and setup guidance.
The manifest presents the skill as a canvas JSON processor, but the body expands capabilities to generic external API integration and broader file/command behaviors. This scope creep is dangerous because it can cause an agent or user to over-trust the skill and invoke it in contexts beyond its declared purpose, increasing the chance of unintended data access, network calls, or unsafe tool use.
The skill documentation says no extra API key is needed, but the security section warns about API key leakage via environment variables and later error guidance discusses API authentication failures. This creates an intent-level contradiction about whether network-authenticated external services are part of the skill's actual operation.
