threejs-debug-profiler
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md and the debug playbook direct the agent to reproduce issues using user-provided commands and URLs. This pattern allows untrusted external data to influence the agent's command execution environment.
- Ingestion points: User-supplied reproduction commands and URLs specified in
SKILL.md(Debug step 1) andreferences/debug-playbook.md(Triage order section). - Boundary markers: Absent. The instructions do not include delimiters or warnings to ignore instructions embedded within the user-provided data.
- Capability inventory: The skill assumes the agent can execute shell commands for reproduction and modify source files to implement fixes (
SKILL.mdsteps 1 and 8). - Sanitization: Absent. There are no instructions for the agent to validate, sanitize, or escape the user-provided commands or URLs before use.
Audit Metadata