guided-learning
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from potentially untrusted sources, including external educational resources and user-editable files.
- Ingestion points: The agent reads content from
MISSION.md,RESOURCES.md,learning-records/, and external URLs designated as knowledge sources. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are mentioned in the files.
- Capability inventory: The skill requires file system read/write access (to manage the workspace) and network access (to fetch resources). It also instructs the agent to open generated HTML content.
- Sanitization: The instructions do not specify any validation or sanitization protocols for content retrieved from external sources before it is incorporated into lessons or records.
- [COMMAND_EXECUTION]: The skill instructions specify that the agent should 'fetch and read the supporting resources' and 'present or open the lesson using the available authorized local workflow.' While these are standard operations for an educational assistant, they involve the execution of network and file-handling tools.
Audit Metadata