skills/tonone-ai/tonone/chaos-game/Gen Agent Trust Hub

chaos-game

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing untrusted data to generate chaos engineering plans.\n- Ingestion points: User input gathered for failure scenarios, participants, environment details, and durations (SKILL.md).\n- Boundary markers: Absent; the instructions do not use delimiters or explicit warnings to ignore instructions embedded in the user context.\n- Capability inventory: The skill environment permits access to tools including 'Bash', 'Write', and 'WebFetch' (SKILL.md frontmatter).\n- Sanitization: Absent; user-provided scenario details are incorporated directly into the plan generation workflow without validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:50 AM
Security Audit — agent-trust-hub — chaos-game