learning-coach
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is limited to managing markdown documents (MISSION.md, LEARNER.md, PLAN.md, LOG.md, RESOURCES.md) within a local directory. It does not request network access or execute shell commands.
- [DATA_EXFILTRATION]: No network operations or data transmission patterns were found. The skill only performs local file operations.
- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages, and it explicitly disables model invocation by default in its frontmatter configuration.
- [PROMPT_INJECTION]: The instructions are focused on educational methodology (active recall, feedback loops) and do not contain patterns attempting to bypass agent safety constraints or reveal system prompts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input to update learning state files. While this technically creates a surface where external content is persisted into the agent's context, the behavior is limited to markdown formatting and serves the primary pedagogical purpose of the skill.
Audit Metadata