launch
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains purely instructional content focused on SaaS launch strategies, Product Hunt optimization, and the ORB marketing framework. No executable scripts, shell commands, or network-active code were found.
- [SAFE]: All external service references (e.g., Product Hunt, SparkToro, Navattic) are to well-known industry platforms and are provided as tactical suggestions for the user rather than automated actions by the agent.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external context from files like
.agents/product-marketing.md. This represents a standard vulnerability surface where untrusted data in the workspace could influence agent behavior, though the risk is mitigated by the skill's lack of high-privilege capabilities. - Ingestion points:
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md. - Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions embedded within these context files.
- Capability inventory: The skill defines no dangerous tools or automated execution capabilities; it primarily provides advice and planning.
- Sanitization: There is no evidence of content filtering or sanitization for the ingested context files.
Audit Metadata