product-launch-checklist

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs and local context files, creating a surface for indirect prompt injection.
  • Ingestion points: The skill fetches content from user-provided URLs (launch assets) and reads local configuration files like .agents/product-context.md.
  • Boundary markers: The skill relies on explicit instructions in the references/house-rules.md (Safety Check 7) which mandates that any fetched or pasted content be treated strictly as data and never as instructions.
  • Capability inventory: The skill is capable of network fetches (URL retrieval) and local file reads within the .agents/ directory.
  • Sanitization: The skill includes a dedicated safety rule to quote rather than execute any instructions found in fetched data and specifically instructs the agent to flag any credentials found in inputs for rotation rather than reproducing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 04:06 PM