notis-skill-creator

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill documents a workflow for packaging local directories into ZIP archives and uploading them to a remote service using a public URL. This process involves accessing local file paths, including the user's home directory (~/.agents/skills/), which is necessary for the skill's synchronization and management features.
  • [COMMAND_EXECUTION]: The instructions direct the agent to use standard system utilities such as mkdir and zip to prepare skill bundles. These operations are restricted to the local development environment and are consistent with the skill's purpose as a creation tool.
  • [INDIRECT_PROMPT_INJECTION]: By design, this skill ingests user-provided text to generate instructions for other agent skills. This creates an attack surface where a user could provide malicious prompts intended to influence the behavior of the newly created skill. The instructions lack explicit guidance on sanitizing these inputs or using boundary markers to prevent the agent from obeying embedded instructions during the creation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 07:43 AM
Security Audit — agent-trust-hub — notis-skill-creator