project-learner
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the system
datecommand to generate precise timestamps for file naming conventions. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to read and continue sessions from previously generated or user-provided Markdown logs.
- Ingestion points: Reads existing learning records or user-provided Markdown log files as described in the session initialization section of SKILL.md.
- Boundary markers: There are no explicit instructions to use delimiters or to disregard potential instructions embedded within the ingested logs.
- Capability inventory: The agent has the capability to execute the
datecommand and perform file system read/write operations within thedocs/directory. - Sanitization: No specific sanitization or content validation steps are outlined for the data read from external or existing log files.
Audit Metadata