skills/swiftyjunnos/skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run CLI commands to open generated HTML lesson files for the user. This is a standard convenience feature for local productivity tools but involves interaction with the host shell.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources and user-generated records (RESOURCES.md, learning-records, etc.). This creates a surface for indirect prompt injection where external content could influence agent behavior.
  • Ingestion points: RESOURCES.md, MISSION.md, NOTES.md, and the ./learning-records/ directory are read to guide agent behavior.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate data from the agent's core instructions.
  • Capability inventory: The agent can write files, read files, and execute shell commands to open files.
  • Sanitization: There is no evidence of input sanitization or filtering for the data read from the workspace files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 04:27 AM
Security Audit — agent-trust-hub — teach