teach
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture is susceptible to indirect prompt injection as it ingests and processes untrusted or user-defined content (Category 8).
- Ingestion points: The agent reads context from
MISSION.md,RESOURCES.md,NOTES.md, and thelearning-records/directory. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from obeying instructions embedded within these ingested files.
- Capability inventory: The agent is authorized to read/write to the file system and execute shell commands to open lessons.
- Sanitization: No content validation or sanitization logic is specified for the ingested resource links or notes.
- [COMMAND_EXECUTION]: The skill instructions advise the agent to use CLI commands to facilitate user interaction, specifically stating: 'If possible, open the lesson file for the user by running a CLI command'. While intended for workflow automation, this utilizes the agent's shell execution capabilities.
- [SAFE]: No obfuscation techniques, hardcoded credentials, unauthorized network exfiltration, or persistence mechanisms were found in the provided instruction set.
Audit Metadata