product-launch
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and strategy frameworks for product launches. There are no scripts, binaries, or automated tool invocations.
- [INDIRECT_PROMPT_INJECTION]: The instructions suggest reading local project context files (e.g.,
.claude/project-context.md). This represents a standard surface for indirect prompt injection where untrusted content in those files could attempt to influence the agent. However, since the skill does not possess high-risk capabilities like shell execution, network exfiltration, or file modification, the risk is minimal. - Ingestion points: SKILL.md (Initial Assessment section)
- Boundary markers: None specified for the project context files.
- Capability inventory: No executable code or tools are present in this skill.
- Sanitization: None.
Audit Metadata