skills/taecontrol/skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided information to generate explanations, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: User conversation context and specific queries (SKILL.md).\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands were identified.\n
  • Capability inventory: The skill instructions mention running the how, why, and show-me skills, and utilizing code, diffs, and debuggers (SKILL.md).\n
  • Sanitization: No sanitization or validation of the ingested user content is specified.\n- [SAFE]: The skill is primarily instructional and does not contain malicious code, remote script execution, obfuscation, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 06:32 PM
Security Audit — agent-trust-hub — teach