product-launch

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read context from external files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md. This practice creates an indirect prompt injection surface where untrusted content in those files could be used to influence the agent's behavior or advice.\n
  • Ingestion points: The skill explicitly checks for and reads project-specific context files at the start of the planning process.\n
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within the marketing context files.\n
  • Capability inventory: The skill is primarily instructional and advisory; it does not contain tools or commands for network operations, file writing, or shell command execution.\n
  • Sanitization: No sanitization or validation logic is specified for the data ingested from the project marketing files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 02:56 PM
Security Audit — agent-trust-hub — product-launch